No
Confirm and Proceed
View More
View Less
Working...
Close
OK
Cancel
Confirm
System Message
Delete
Schedule
An unknown error has occurred and your request could not be completed. Please contact support.
Reserved - Scan in at least 10 minutes before the beginning of the session or you forfeit your seat.
This has been added to your Planner. Please note this is first come, first served. You have not reserved a seat in this activity.
Waitlisted - You may be assigned a reserved seat if one becomes available.

In order to find repeats of this session, please click on the session title to view the session details.
Personal Calendar
 
Conference Event
Meeting
Interests
There aren't any available sessions at this time.
System Message
This session is already scheduled at another time. Would you like to...
Loading...
Please enter a maximum of {0} characters.
{0} remaining of {1} character maximum.
Please enter a maximum of {0} words.
{0} remaining of {1} word maximum.
must be 50 characters or less.
must be 40 characters or less.
Session Summary
We were unable to load the map image.
This has not yet been assigned to a map.
Search Catalog
Reply
Replies ()
Search
New Post
Microblog
Microblog Thread
Post Reply
Post
Your session timed out.
Meeting Summary

I'm interested in this
I'm no longer interested
 

ACT01 - Midnight Madness Midnight Madness provides a sneak peek into re:Invent, complete with fun, drinks, and snacks. There will be a chicken wing eating contest, marching bands, conga lines, street performers, and much, much more - don't miss it! Activity
ACT02 - Tatonka Join us at Midnight Madness to discover and witness re:Invent's famous chicken wing eating extravaganza - Tatonka. Reserve your seat in advance. Tatonka
ACT05 - Ping Pong Tournament #1 The AWS Ping Pong Tournament returns to re:Invent, with games on Wednesday and Thursday. Activity
ACT06 - Ping Pong Tournament #2 The AWS Ping Pong Tournament returns to re:Invent, with games on Wednesday and Thursday. Activity
ACT07 - Bingo Night (Venetian) Back by popular demand, Bingo Night returns to re:Invent across two venues. Activity
ACT08 - Bingo Night (Aria) Back by popular demand, Bingo Night returns to re:Invent across two venues. Activity
ACT09 - Board Game Night Relax with fellow attendees over snacks and a game or two of whatever you're into. We'll have all the classics and much more. Activity
ACT10 - Arts & Crafts Looking for something creative and relaxing to help you unwind? Grab a beverage to sip on while painting your own masterpiece. Reserve your seat in advance. Activity
ACT11 - Movie Night (Venetian) Grab some popcorn and get ready to watch cult classics and best-loved films of the '80s! Doors open at 7:00 PM. Activity
ACT12 - Movie Night (Aria) Grab some popcorn and get ready to watch cult classics and best-loved films of the '80s! Doors open at 7:00 PM. Activity
ACT13 - Broomball For those of you who always wanted to play Quidditch in school, broomball is for you. We'll explain everything just bring yourself! Activity
ACT14 - Dodgeball Remember the 5 Ds of dodgeball: “Dodge, duck, dip, dive, and dodge.” If you can live by those wise words, you’ll fit right in at our annual dodgeball showdown! Activity
ACT15 - Choir! Choir! Choir! Ready to sing your heart out alongside your fellow attendees? Reserve your spot to join the choir! Activity
ADM201-L - Leadership session: Digital marketing and ad technology In this session meant for executive leaders, you get to see the AWS vision for how companies stand out in the crowded, massively scaled advertising and marketing ecosystem. Industry leaders share stories about how they used AWS to enable breakthroughs in areas such as customer data collection, identity resolution, audience targeting, programmatic advertising, personalization, and measurement. Then we turn to the future and share our playbook for artificial intelligence and real-time solutions for transforming big data into marketing outcomes. Session Dmitri Tchikatilov Calvin French-Owen Scott N Brown Zak Stengel Srini Varadarajan
ADM203 - Reimagining advertising analytics & identity resolution at scale Most companies in Advertising & Marketing run some kind of big data workload. But are they taking advantage of the latest cloud technology? In this session, learn how AWS customers can optimize data collection, analytics, and identity resolution using containers, serverless computing, and graph databases. Customers share detailed technical best practices for big data and advertising analytics at massive scale and low cost. Then we dive deep into an example of how to improve identity matching and audience targeting using Amazon Neptune and other AWS tools. Session Dmitri Tchikatilov Sasikala Singamaneni Eric Whitney Christopher Hansen
ADM301 - Best practices for identity resolution with Amazon Neptune In this chalk talk, learn how to build a cloud-centric, graph-based identity resolution system that connects customer data across devices, channels, and touchpoints and helps enable better media buying and personalization. Learn about best practices and the mistakes to avoid for identity resolution data collection, processing, and preparation. We deep dive into architectural details for achieving high availability and low latency at scale using AWS services such as Amazon EMR, Amazon Neptune, Amazon EC2, and Amazon S3. We also discuss recommendations for using Neptune as a fully managed graph database service for identity resolution. Chalk Talk Taylor Riggan Nitin Poddar
ADM302 - End-to-end machine learning using Spark and Amazon SageMaker Learn how AWS customers are developing production-ready machine learning models to optimize auction dynamics and bid pricing—all within the millisecond latency requirements of programmatic ad buying. Forget “hello world” ML tutorials; instead we dive deep into an example of how to train models for terabyte-scale advertising data cost-effectively. Find out how to create environments for machine learning engineers so they can prototype and explore with TensorFlow before executing it in distributed systems using Spark and Amazon SageMaker. We explain productionizing models and deployment, which we then back up with real-life examples. Session Dmitri Tchikatilov François Guerraz Janko Kovacevic
ADM303 - Implementing Amazon Personalize across marketing channels Amazon Personalize makes it easy to train machine learning models based on the behavioral data of your customers. However, putting these models into practice across marketing channels to deliver high-quality customer experiences still requires some lifting on your end. In this chalk talk, we discuss the best practices and strategies for implementing Amazon Personalize—including what we’ve seen work and what we’ve seen doesn’t—to create personalized customer experiences across multiple digital channels, including web, mobile, and messaging. Chalk Talk Dylan Tong James Jory
ADM401 - Analyzing Amazon DSP data in an AWS data lake Advertisers and agencies working with Amazon DSP are interested in analyzing available data points to understand segment and campaign performance. In this one-hour lab meant for companies working with Amazon DSP today, we show how to set up an AWS data lake based on reporting files from Amazon DSP in Amazon Simple Storage Service (Amazon S3) in order to analyze and visualize the data. We show you how to use AWS Glue Data Catalog to crawl and create a data source, use Amazon Athena for extraction, and display the data in Amazon QuickSight. Builders Session David Beck
ADM402 - Testing techniques for measuring personalization In this hands-on lab, you sit down with an AWS solutions architect to learn how to integrate techniques such as A/B, multi-armed bandit, and interleaved recommendation testing to measure effectiveness of machine learning for personalization. You’ll come away knowing how to build an end-to-end solution for deploying recommendation models using Amazon Personalize that integrates with measurement techniques that can be applied to customer experience in e-commerce or other marketing channels. Builders Session James Jory
AIM201-S - Hot paths to anomaly detection with TIBCO data science, streaming on AWS Sensor data on the event stream can be voluminous. In NAND manufacturing, there are millions of columns of data that represent many measured and virtual metrics. These sensor data can arrive with considerable velocity. In this session, learn about developing cross-sectional and longitudinal analyses for anomaly detection and yield optimization using deep learning methods, as well as super-fast subsequence signature search on accumulated time-series data and methods for handling very wide data in Apache Spark on Amazon EMR. The trained models are developed in TIBCO Data Science and Amazon SageMaker and applied to event streams using services such as Amazon Kinesis to identify hot paths to anomaly detection. This presentation is brought to you by TIBCO Software, an APN Partner. Session Michael OConnell Steve Hillion
AIM202-S - Artificial intelligence in Healthcare SENTRI is an intelligent automation application platform built leveraging native AWS components to facilitate case processing in the Healthcare industry. PwC built an engine that can take in an adverse healthcare/level of service (HC/LS) event case, extract key information, provide an initial interpretation of severity, and triage the case for review. PwC performed analysis using a user-centric experience, which allowed the case processor to easily verify outputs and helped build trust and confidence in the machine’s interpretation. In this session, learn how a PwC customer has been successfully using this system for over nine months. It used to take two hours to process a case. Now, it takes three seconds. This presentation is brought to you by PwC, an APN Partner. Session Matthew Rich
AIM203-S - Take AI/ML from theory to practice with Intel technologies on AWS The challenges associated with scalability have been removed in the cloud. Today, organizations deploy tons of artificial intelligence/machine learning (AI/ML) workloads on AWS. Learn about how easy and cost-effective it is to build customized, intelligent data models leveraging the full power of Intel Xeon Scalable processors. Also, learn how you can rapidly train, deploy, and operationalize AI/ML and big data applications on AWS. This presentation is brought to you by Intel, an APN Partner. Session
AIM204-S - Discovering the value of a cloud data platform In this session, Discover Financial Services and Accenture discuss their work with moving Discover from an on-premises data infrastructure to the AWS Cloud, which offers advanced analytics. With an intelligent data strategy and fully optimized AWS Cloud data solution, Discover is transforming the customer experience and increasing shareholder value. Today, the bank leverages data from many sources—structured and unstructured, streaming and batch—and analyzes the data for insights. This strategy required a bold pivot from a legacy, on-premises architecture to a fully integrated data platform on the cloud. Learn how Discover is also successfully navigating the cultural changes of this type of transformation. This presentation is brought to you by Accenture, an APN Partner. Session Arunashish Majumdar Chad Duncan Michael Oppenheim
AIM205 - Starting the enterprise machine learning journey, featuring ProSieben Amazon has been investing in machine learning for more than 20 years, innovating in areas such as fulfillment and logistics, personalization and recommendations, forecasting, fraud prevention, and supply chain optimization. During this session, we take this expertise and show you how to identify business problems that can be solved with machine learning. We discuss considerations including selecting the right use case for a machine learning pilot, nurturing skills, and measuring the success of such pilots. We dive into success stories from the Amazon ML Solutions Lab, and you can hear from ProSieben about how it moved from idea to production with machine learning. Session Jason Gelman Priya Ponnapalli Kiran Kulkarni
AIM206-R - [REPEAT] Finding a needle in a haystack: Use AI to transform content management Finding digital content, from documents to media, can be frustrating and time-consuming. Across your employees or customers, this challenge can waste hours, derail projects, and create poor experiences. In this breakout session, learn how to use language and vision AI services to extract data, insights, and trends from all of your digital content, with a focus on how to more effectively manage your documents and find what you need. Session Udi Hershkovich Niranjan Hira Girish Arunagiri
AIM206-R1 - [REPEAT 1] Finding a needle in a haystack: Use AI to transform content management Finding digital content, from documents to media, can be frustrating and time-consuming. Across your employees or customers, this challenge can waste hours, derail projects, and create poor experiences. In this breakout session, learn how to use language and vision AI services to extract data, insights, and trends from all of your digital content, with a focus on how to more effectively manage your documents and find what you need. Session Udi Hershkovich Niranjan Hira Girish Arunagiri
AIM207-R - [REPEAT] Get started with AWS DeepRacer Get behind the keyboard for an immersive experience with AWS DeepRacer. Developers with no prior machine learning experience learn new skills and apply their knowledge in a fun and exciting way. With the help of the AWS pit crew, build and train a reinforcement learning model that you can race on the tracks in the MGM Grand Garden Arena and win special AWS prizes! Workshop Donnie Prakoso Brian Townsend
AIM207-R1 - [REPEAT 1] Get started with AWS DeepRacer Get behind the keyboard for an immersive experience with AWS DeepRacer. Developers with no prior machine learning experience learn new skills and apply their knowledge in a fun and exciting way. With the help of the AWS pit crew, build and train a reinforcement learning model that you can race on the tracks in the MGM Grand Garden Arena and win special AWS prizes! Workshop OLIVIER BERGERET Eduardo Calleja
AIM207-R2 - [REPEAT 2] Get started with AWS DeepRacer Get behind the keyboard for an immersive experience with AWS DeepRacer. Developers with no prior machine learning experience learn new skills and apply their knowledge in a fun and exciting way. With the help of the AWS pit crew, build and train a reinforcement learning model that you can race on the tracks in the MGM Grand Garden Arena and win special AWS prizes! Workshop Sunil Mallya
AIM207-R3 - [REPEAT 3] Get started with AWS DeepRacer Get behind the keyboard for an immersive experience with AWS DeepRacer. Developers with no prior machine learning experience learn new skills and apply their knowledge in a fun and exciting way. With the help of the AWS pit crew, build and train a reinforcement learning model that you can race on the tracks in the MGM Grand Garden Arena and win special AWS prizes! Workshop Tim O'Brien Todd Escalona
AIM207-R4 - [REPEAT 4] Get started with AWS DeepRacer Get behind the keyboard for an immersive experience with AWS DeepRacer. Developers with no prior machine learning experience learn new skills and apply their knowledge in a fun and exciting way. With the help of the AWS pit crew, build and train a reinforcement learning model that you can race on the tracks in the MGM Grand Garden Arena and win special AWS prizes! Workshop Francois van Rensburg Muhyun Kim
AIM207-R5 - [REPEAT 5] Get started with AWS DeepRacer Get behind the keyboard for an immersive experience with AWS DeepRacer. Developers with no prior machine learning experience learn new skills and apply their knowledge in a fun and exciting way. With the help of the AWS pit crew, build and train a reinforcement learning model that you can race on the tracks in the MGM Grand Garden Arena and win special AWS prizes! Workshop Ben Thurgood Sunil Mallya
AIM207-R6 - [REPEAT 6] Get started with AWS DeepRacer Get behind the keyboard for an immersive experience with AWS DeepRacer. Developers with no prior machine learning experience learn new skills and apply their knowledge in a fun and exciting way. With the help of the AWS pit crew, build and train a reinforcement learning model that you can race on the tracks in the MGM Grand Garden Arena and win special AWS prizes! Workshop Donnie Prakoso Brian Townsend
AIM207-R7 - [REPEAT 7] Get started with AWS DeepRacer Get behind the keyboard for an immersive experience with AWS DeepRacer. Developers with no prior machine learning experience learn new skills and apply their knowledge in a fun and exciting way. With the help of the AWS pit crew, build and train a reinforcement learning model that you can race on the tracks in the MGM Grand Garden Arena and win special AWS prizes! Workshop OLIVIER BERGERET Eduardo Calleja
AIM207-R8 - [REPEAT 8] Get started with AWS DeepRacer Get behind the keyboard for an immersive experience with AWS DeepRacer. Developers with no prior machine learning experience learn new skills and apply their knowledge in a fun and exciting way. With the help of the AWS pit crew, build and train a reinforcement learning model that you can race on the tracks in the MGM Grand Garden Arena and win special AWS prizes! Workshop Francois van Rensburg Muhyun Kim
AIM207-R9 - [REPEAT 9] Get started with AWS DeepRacer Get behind the keyboard for an immersive experience with AWS DeepRacer. Developers with no prior machine learning experience learn new skills and apply their knowledge in a fun and exciting way. With the help of the AWS pit crew, build and train a reinforcement learning model that you can race on the tracks in the MGM Grand Garden Arena and win special AWS prizes! Workshop Eric Sun Tim O'Brien
AIM208-R - [REPEAT] Transform the way you search and interact with enterprise data using AI How can you get the most intuitive and specific answer to a search query when the answer may be hidden within various enterprise filing or information systems? This session teaches you how to use natural language processing, a machine learning technique, to build an enterprise search solution that will give you straightforward answers to questions like, “How much is the cash reward on the corporate credit card?” Learn how this can improve cross-team knowledge sharing, enhance sales and customer support services, and make it much easier for end customers to find the information they need. Session Vikram Anbazhagan Jean-Pierre Dodel
AIM208-R1 - [REPEAT 1] Transform the way you search and interact with enterprise data using AI How can you get the most intuitive and specific answer to a search query when the answer may be hidden within various enterprise filing or information systems? This session teaches you how to use natural language processing, a machine learning technique, to build an enterprise search solution that will give you straightforward answers to questions like, “How much is the cash reward on the corporate credit card?” Learn how this can improve cross-team knowledge sharing, enhance sales and customer support services, and make it much easier for end customers to find the information they need. Session Vikram Anbazhagan Jean-Pierre Dodel
AIM210 - Transforming Healthcare with AI Improving patient care, making treatment decisions, managing clinical trials, and more are all moving into a new age due to advancements in AI. In this session, we cover AI solutions specific to the Healthcare industry, from extracting relevant medical information from patient records and clinical trial reports to automating the clinical documentation process with automatic speech recognition. Hear directly from our customers and come away with answers on how to get started immediately. Session Paul Zhao Arun Ravi
AIM211 - AI document processing for business automation Millions of times per day, customers from the Finance, Healthcare, public, and other sectors rely on information that is locked in documents. Amazon Textract uses artificial intelligence to "read" such documents as a person would, to extract not only text but also tables, forms, and other structured data without configuration, training, or custom code. In this session, we demonstrate how you can use Amazon Textract to automate business processes with AI. You also hear directly from our customers about how they accelerated their own business processes with Amazon Textract. Session Kriti Bharti Jon Turow Siddharth Ram
AIM212 - ML in retail: Solutions that add intelligence to your business Machine learning is ranked the number-one “game changer” for the retail market segment by chief experience officers (CXOs), yet it’s only number eight on top spending priorities. So which scenarios are real? In this session, we dive into how AWS puts machine learning in the hands of every developer, without the need for deep machine learning experience. Learn about personalized product recommendations, inventory forecasting, new in-store experiences, and more. Learn from our experience at Amazon.com and hear from our customers today. Session Ben Thurgood Samir Araujo
AIM213-R - [REPEAT] Improve machine learning model quality in response to changes in data Machine learning models are typically trained and evaluated using historical data. But the real-world data may not look like the training data, especially as models age over time and the distribution of data changes. This gradual variance of the model from the real world is known as model drift, and it can have a big impact on prediction quality. This session explores techniques you can use to monitor prediction quality in production, as well as effective corrective actions such as auditing and iterative retraining.     Session Urvashi Chowdhary
AIM213-R1 - [REPEAT 1] Improve machine learning model quality in response to changes in data Machine learning models are typically trained and evaluated using historical data. But the real-world data may not look like the training data, especially as models age over time and the distribution of data changes. This gradual variance of the model from the real world is known as model drift, and it can have a big impact on prediction quality. This session explores techniques you can use to monitor prediction quality in production, as well as effective corrective actions such as auditing and iterative retraining. Session Urvashi Chowdhary
AIM218-L - Leadership session: Machine learning We are embarking on the golden age of machine learning. Many of the constraints that typically held back the application of machine learning in the real world are starting to disappear. AWS offers a significant breadth and depth of cloud services. In this leadership session, we explore the democratization of machine learning and how the growth of cloud services makes it easy for customers to move from idea to production with machine learning. Session Swami Sivasubramanian
AIM220-S - Farmers Insurance elevating customer experience with conversational AI As part of its digital transformation journey, Farmers, one of America’s largest insurers, envisioned digitizing its customer and agent service experience. Join Farmers for this insightful session, and learn how it leveraged conversational artificial intelligence (AI), chatbots, and other next-generation AWS technologies to offer a seamless, personalized, and contextualized experience for agents and customers. Learn how Farmers improved customer experience and optimized resources while encouraging self-service with cloud-based services, automation, and AI. Also, gain insights on how to design, architect, and build a scalable conversational AI solution that caters to growing business demands. This presentation is brought to you by Cognizant, an APN Partner. Session Arjun Chatterjee Joseph Stellin
AIM222-R - [REPEAT] Monetizing text-to-speech AI In this interactive session, we look at different options to monetize text-to-voice applications. We focus on Amazon Polly, a machine learning–powered service that produces lifelike speech. You learn to monetize this capability and generate a positive ROI when creating Amazon Polly applications. This chalk talk covers both business and technical considerations. Chalk Talk Robin Dautricourt Ron Jaworski
AIM222-R1 - [REPEAT 1] Monetizing text-to-speech AI In this interactive session, we look at different options to monetize text-to-voice applications. We focus on Amazon Polly, a machine learning–powered service that produces lifelike speech. You learn to monetize this capability and generate a positive ROI when creating Amazon Polly applications. This chalk talk covers both business and technical considerations. Chalk Talk Robin Dautricourt Ron Jaworski
AIM224 - Use pretrained models and algorithms in AWS Marketplace You can cut down on development time for machine learning projects with third-party algorithms and models in a secure environment using Amazon SageMaker. Learn how in this chalk talk, as we walk through the subscription, evaluation, and deployment process for algorithms as well as pretrained models from AWS Marketplace. Chalk Talk Kanchan Waikar
AIM225 - How to build a car that does an 8.64-second lap with AWS DeepRacer Deep dive on AWS DeepRacer! In this chalk talk, learn how to build a race-winning model from a 2019 AWS Summit Circuit race winner and get tips on how you can excel in the AWS DeepRacer league in 2020. Chalk Talk Chun Yin Wong Kwai Hung Chong
AIM226 - How to successfully become a machine learning developer In this chalk talk, learn how to get started building, training, and deploying your first machine learning model. We then discuss tips, tricks, and best practices on starting your machine learning journey. Chalk Talk Kesha Williams Alexander Schultz
AIM229 - Start using computer vision with AWS DeepLens If you're new to deep learning, this workshop is for you. Learn how to build and deploy computer-vision models using the AWS DeepLens deep-learning-enabled video camera. Also learn how to build a machine learning application and a model from scratch using Amazon SageMaker. Finally, learn to extend that model to Amazon SageMaker to build an end-to-end AI application. Workshop Phu Nguyen Nathaniel Slater
AIM231-S - Think Forward Initiative: 100M people making better financial decisions Want to learn more about using technology to impact society? Join this session! Currently, 42 percent of Europeans face financial difficulties. As lead partners of the Think Forward Initiative (TFI), Deloitte, AWS, and ING aim to empower 100 million Europeans to make better financial decisions by translating the latest consumer behavior insights into easy applicable tools. In this session, you learn how TFI supports early stage scale-ups by using Amazon S3, Amazon API Gateway, AWS Lambda, Amazon Aurora, AWS CloudFormation, AWS Cloud9, Amazon Textract, and Amazon Personalize in an accelerator program. You also learn about the AWS Well-Architected Review and AWS Activate programs. This presentation is brought to you by Deloitte, an APN Partner. Session Adam Simpson Dagmar van der Plas Joep Arends
AIM301-R - [REPEAT] Creating high-quality training datasets with data labeling Amazon SageMaker Ground Truth makes it easy to quickly label high-quality, accurate training datasets. In this workshop, we set up labeling jobs for text and images to help you understand how to make the most of Amazon SageMaker Ground Truth. You learn how to explore and prepare the dataset and label it with object bounding boxes. Then, we use Amazon SageMaker to train a Single Shot MultiBox Detector (SSD) object-detection model based on the labeled dataset, use hyperparameter optimization to find the best model for deployment, and deploy the model to an endpoint for use in an application. Workshop Will Badr Denis V Batalov
AIM301-R1 - [REPEAT 1] Creating high-quality training datasets with data labeling Amazon SageMaker Ground Truth makes it easy to quickly label high-quality, accurate training datasets. In this workshop, we set up labeling jobs for text and images to help you understand how to make the most of Amazon SageMaker Ground Truth. You learn how to explore and prepare the dataset and label it with object bounding boxes. Then, we use Amazon SageMaker to train a Single Shot MultiBox Detector (SSD) object-detection model based on the labeled dataset, use hyperparameter optimization to find the best model for deployment, and deploy the model to an endpoint for use in an application. Workshop Denis V Batalov Will Badr
AIM302-R - [REPEAT] Create a Q&A bot with Amazon Lex and Amazon Alexa A recent poll showed that 44 percent of customers would rather talk to a chatbot than to a human for customer support. In this workshop, we show you how to deploy a question-and-answer bot using two open-source projects: QnABot and Lex-Web-UI. You get started quickly using Amazon Lex, Amazon Alexa, and Amazon Elasticsearch Service (Amazon ES) to provide a conversational chatbot interface. You enhance this solution using AWS Lambda and integrate it with Amazon Connect. Workshop Bob Potterveld Bob Strahan
AIM302-R1 - [REPEAT 1] Create a Q&A bot with Amazon Lex and Amazon Alexa A recent poll showed that 44 percent of customers would rather talk to a chatbot than to a human for customer support. In this workshop, we show you how to deploy a question-and-answer bot using two open-source projects: QnABot and Lex-Web-UI. You get started quickly using Amazon Lex, Amazon Alexa, and Amazon Elasticsearch Service (Amazon ES) to provide a conversational chatbot interface. You enhance this solution using AWS Lambda and integrate it with Amazon Connect. Workshop Bob Potterveld Bob Strahan
AIM303-R - [REPEAT] Stop guessing: Use AI to understand customer conversations You don't need to be a data scientist to build an AI application. In this workshop, we show you how to use AWS AI services to build a serverless application that you can use to understand your customer interactions. Analyze call-center recordings with the help of automatic speech recognition, translation, and natural language processing (NLP). Get hands-on by producing your own call recordings using Amazon Connect. In the last step of this workshop, set up a processing pipeline to automate transcription and NLP analysis, and run analytics and visualizations on the results. Workshop Dirk Froehner Boaz Ziniman
AIM303-R1 - [REPEAT 1] Stop guessing: Use AI to understand customer conversations You don't need to be a data scientist to build an AI application. In this workshop, we show you how to use AWS AI services to build a serverless application that you can use to understand your customer interactions. Analyze call-center recordings with the help of automatic speech recognition, translation, and natural language processing (NLP). Get hands-on by producing your own call recordings using Amazon Connect. In the last step of this workshop, set up a processing pipeline to automate transcription and NLP analysis, and run analytics and visualizations on the results. Workshop Boaz Ziniman Dirk Froehner
AIM304-R - [REPEAT] Build a content-recommendation engine with Amazon Personalize Machine learning is being used increasingly to improve customer engagement by powering personalized product and content recommendations. Amazon Personalize lets you easily build sophisticated personalization capabilities into your applications, using machine learning technology perfected from years of use on Amazon.com. In this workshop, you build your own recommendation engine by providing training data, building a model based on the algorithm of your choice, testing the model by deploying your Amazon Personalize campaign, and integrating it into your own application. Workshop Gaurav Chauhan Chris King
AIM304-R1 - [REPEAT 1] Build a content-recommendation engine with Amazon Personalize Machine learning is being used increasingly to improve customer engagement by powering personalized product and content recommendations. Amazon Personalize lets you easily build sophisticated personalization capabilities into your applications, using machine learning technology perfected from years of use on Amazon.com. In this workshop, you build your own recommendation engine by providing training data, building a model based on the algorithm of your choice, testing the model by deploying your Amazon Personalize campaign, and integrating it into your own application. Workshop Gaurav Chauhan Chris King
AIM305-R - [REPEAT] Automate content moderation and compliance with AI Brand safety is a major concern as advertising becomes more automated. Issues with ad adjacency arise, contracts with brands or celebrities run out, and user-generated content can be difficult to manage. In this workshop, you learn how to use Amazon Rekognition, Amazon Textract, and Amazon Comprehend to detect inappropriate content or noncompliant use of content such as logos or celebrity faces. You leave with a scalable architecture that will save days of manual review in media moderation and compliance workflows. Workshop Kashif Imran Niranjan Hira
AIM305-R1 - [REPEAT 1] Automate content moderation and compliance with AI Brand safety is a major concern as advertising becomes more automated. Issues with ad adjacency arise, contracts with brands or celebrities run out, and user-generated content can be difficult to manage. In this workshop, you learn how to use Amazon Rekognition, Amazon Textract, and Amazon Comprehend to detect inappropriate content or noncompliant use of content such as logos or celebrity faces. You leave with a scalable architecture that will save days of manual review in media moderation and compliance workflows. Workshop Niranjan Hira Kashif Imran
AIM306-R - How to build high-performance ML solutions at low cost, featuring Aramex Amazon SageMaker helps provide the best model performance for less cost. In this session, we walk through a TCO analysis of Amazon SageMaker, exploring its three modules—build, train, and deploy. Learn how Amazon SageMaker automatically configures and optimizes ML frameworks such as TensorFlow, MXNet, and PyTorch, and see how to use pre-built algorithms that are tuned for scale, speed, and accuracy. We explain how the automatic model tuning feature performs hyperparameter optimization by discovering interesting features in your data and learning how those features interact to affect accuracy. Learn how to deploy your model with one click and how to lower inference costs using Amazon Elastic Inference. We end by showing how Aramex uses Amazon SageMaker. Session Mark Roy Mohammed Sleeq
AIM306-R1 - [REPEAT 1] How to build high-performance machine learning solutions at low cost Amazon SageMaker helps provide the best model performance for less cost. In this session, we walk through a TCO analysis of Amazon SageMaker, exploring its three modules—build, train, and deploy. Learn how Amazon SageMaker automatically configures and optimizes ML frameworks such as TensorFlow, MXNet, and PyTorch, and see how to use pre-built algorithms that are tuned for scale, speed, and accuracy. We explain how the automatic model tuning feature performs hyperparameter optimization by discovering interesting features in your data and learning how those features interact to affect accuracy. Learn how to deploy your model with one click and how to lower inference costs using Amazon Elastic Inference. We end by showing how Siemens uses Amazon SageMaker to manage costs. Session Mark Roy Carlos Cunha Rodrigues Jan Pospisil
AIM307 - Amazon SageMaker deep dive: A modular solution for machine learning Amazon SageMaker is a fully managed service that offers developers and data scientists the flexibility to build, train, and deploy machine learning models through modular capabilities. In this session, we dive deep into the technical details of each module so you understand how to label and prepare your data, choose an algorithm, train and optimize the model, and make predictions. We also discuss practical deployments of Amazon SageMaker through real-world customer examples. Session Shyam Srinivasan Julien Simon Nils Mohr
AIM308 - Build accurate training datasets with Amazon SageMaker Ground Truth Successful machine learning models are built on high-quality training datasets. Typically, the task of data labeling is distributed across a large number of humans, adding significant overhead and cost. This session explains how Amazon SageMaker Ground Truth reduces cost and complexity using techniques designed to improve labeling accuracy and reduce human effort. We walk through best practices for building highly accurate training datasets and discuss how you can use Amazon SageMaker Ground Truth to implement them. Session Vikram Madan
AIM310-S - Why observability requires the marriage of AI, metrics, and logs The new digital world presents great opportunity as workloads move to the cloud and containers and companies benefit from serverless computing and an agile application delivery chain. However, these opportunities come with significant challenges. Site reliability engineers have been tasked with knitting together disparate platforms to build an observable stack, which is imperative for early detection of service degradation issues. We demonstrate a novel alternative that combines metrics, logs, and alerts into a comprehensive AIOps approach. Learn how to deliver an AI-enabled service that provides instant observability of your cloud application stack and how to combine logs and metrics into a single pane of glass. This presentation is brought to you by Moogsoft, an APN Partner. Session Phil Tee
AIM311-R - [REPEAT] Choose the right instance type in Amazon SageMaker Amazon SageMaker, a fully managed service for machine learning, offers several compute capabilities and instance types to meet the needs of your use case. In this session, we review the compute options available to you, including GPUs, CPUs, AWS Inferentia, Amazon SageMaker Neo, and Amazon Elastic Inference. We discuss best practices and key criteria to choose the right capabilities that meet the specific needs of your machine learning workload. Session Srinivas Hanabe Yuval Fernbach
AIM311-R1 - [REPEAT 1] Choose the right instance type in Amazon SageMaker Amazon SageMaker, a fully managed service for machine learning, offers several compute capabilities and instance types to meet the needs of your use case. In this session, we review the compute options available to you, including GPUs, CPUs, AWS Inferentia, Amazon SageMaker Neo, and Amazon Elastic Inference. We discuss best practices and key criteria to choose the right capabilities that meet the specific needs of your machine learning workload. Session Srinivas Hanabe Yuval Fernbach
AIM312 - Predict future business outcomes using Amazon Forecast Based on the same technology used at Amazon.com, Amazon Forecast uses machine learning and time-series data to build accurate business forecasts. In this session, learn how machine learning can improve accuracy in demand forecasting, financial planning, and resource allocation while reducing your forecasting time from months to hours. Session Chris King Rohit Menon Sean McCrary
AIM313-R - [REPEAT] Adding computer vision to your applications Companies are using computer vision to understand the content and context of their images and videos, at scale. This breakout session provides an overview of the nuances to consider when developing your own application. We discuss multiple approaches to solve the computer-vision needs of your business and next steps to develop a model for your specific use case. Session Vamsi Vutukuru Anushri Mainthia
AIM313-R1 - [REPEAT 1] Adding computer vision to your applications Companies are using computer vision to understand the content and context of their images and videos, at scale. This breakout session provides an overview of the nuances to consider when developing your own application. We discuss multiple approaches to solve the computer-vision needs of your business and next steps to develop a model for your specific use case. Session Vamsi Vutukuru Anushri Mainthia
AIM315-R - [REPEAT] Amazon SageMaker: Bring your own algorithm In this builders session, get hands-on in the Amazon SageMaker console and learn to package your own script or algorithm to use with Amazon SageMaker. See how to use any programming language or framework to develop your container. We walk through the Bring Your Own R Algorithm example on GitHub. Builders Session Yuval Fernbach
AIM315-R1 - [REPEAT 1] Amazon SageMaker: Bring your own algorithm In this builders session, get hands-on in the Amazon SageMaker console and learn to package your own script or algorithm to use with Amazon SageMaker. See how to use any programming language or framework to develop your container. We walk through the Bring Your Own R Algorithm example on GitHub. Builders Session Yuval Fernbach
AIM316-R - [REPEAT] Amazon SageMaker: Prebuilt algorithms In this builders session, learn how to use the range of built-in, high-performance machine learning algorithms that come with Amazon SageMaker. We go into the console and explore how to pick and choose the best algorithms for your machine learning use case, such as fraud detection, forecasting, image classification, churn prediction, customer targeting, log processing and anomaly detection, and speech-to-text. We explain how AWS optimizes the algorithms for scale, speed, and accuracy. Builders Session Zdravko Pantic
AIM316-R1 - [REPEAT 1] Amazon SageMaker: Prebuilt algorithms In this builders session, learn how to use the range of built-in, high-performance machine learning algorithms that come with Amazon SageMaker. We go into the console and explore how to pick and choose the best algorithms for your machine learning use case, such as fraud detection, forecasting, image classification, churn prediction, customer targeting, log processing and anomaly detection, and speech-to-text. We explain how AWS optimizes the algorithms for scale, speed, and accuracy. Builders Session Zdravko Pantic
AIM316-R2 - [REPEAT 2] Amazon SageMaker: Prebuilt algorithms In this builders session, learn how to use the range of built-in, high-performance machine learning algorithms that come with Amazon SageMaker. We go into the console and explore how to pick and choose the best algorithms for your machine learning use case, such as fraud detection, forecasting, image classification, churn prediction, customer targeting, log processing and anomaly detection, and speech-to-text. We explain how AWS optimizes the algorithms for scale, speed, and accuracy. Builders Session Zdravko Pantic
AIM316-R3 - [REPEAT 3] Amazon SageMaker: Prebuilt algorithms In this builders session, learn how to use the range of built-in, high-performance machine learning algorithms that come with Amazon SageMaker. We go into the console and explore how to pick and choose the best algorithms for your machine learning use case, such as fraud detection, forecasting, image classification, churn prediction, customer targeting, log processing and anomaly detection, and speech-to-text. We explain how AWS optimizes the algorithms for scale, speed, and accuracy. Builders Session Zdravko Pantic
AIM317-R - [REPEAT] Amazon SageMaker: Train a model in a single click In this builders session, we show you how to scale your machine learning training environments. Using the Amazon SageMaker console, you can begin training your model with a single click and reduce your training costs by up to 90 percent with Managed Spot Training. Amazon SageMaker handles all of the underlying infrastructure to scale up to petabyte-sized datasets easily. After your training environment is set up, you will deploy your model with a single click either in the cloud or on edge devices. Builders Session Zdravko Pantic
AIM317-R1 - [REPEAT 1] Amazon SageMaker: Train a model in a single click In this builders session, we show you how to scale your machine learning training environments. Using the Amazon SageMaker console, you can begin training your model with a single click and reduce your training costs by up to 90 percent with Managed Spot Training. Amazon SageMaker handles all of the underlying infrastructure to scale up to petabyte-sized datasets easily. After your training environment is set up, you will deploy your model with a single click either in the cloud or on edge devices. Builders Session Zdravko Pantic
AIM318-R - [REPEAT] Amazon SageMaker: Automatically tune hyperparameters Amazon SageMaker offers automatic model tuning so you can use machine learning to quickly tune your model to be as accurate as possible. This capability lets you skip the tedious trial-and-error process of manually adjusting model parameters. Instead, over multiple training runs, automatic model tuning performs hyperparameter optimization by discovering interesting features in your data and learning how those features interact to affect accuracy. In this builders session, we show you how to configure and launch a hyperparameter tuning job. Builders Session Cyrus Vahid
AIM318-R1 - [REPEAT 1] Amazon SageMaker: Automatically tune hyperparameters Amazon SageMaker offers automatic model tuning so you can use machine learning to quickly tune your model to be as accurate as possible. This capability lets you skip the tedious trial-and-error process of manually adjusting model parameters. Instead, over multiple training runs, automatic model tuning performs hyperparameter optimization by discovering interesting features in your data and learning how those features interact to affect accuracy. In this builders session, we show you how to configure and launch a hyperparameter tuning job. Builders Session Cyrus Vahid
AIM318-R2 - [REPEAT 2] Amazon SageMaker: Automatically tune hyperparameters Amazon SageMaker offers automatic model tuning so you can use machine learning to quickly tune your model to be as accurate as possible. This capability lets you skip the tedious trial-and-error process of manually adjusting model parameters. Instead, over multiple training runs, automatic model tuning performs hyperparameter optimization by discovering interesting features in your data and learning how those features interact to affect accuracy. In this builders session, we show you how to configure and launch a hyperparameter tuning job. Builders Session Cyrus Vahid
AIM319-R - [REPEAT] Amazon SageMaker: Use prebuilt Jupyter notebooks In this builders session, we show you how to bring an existing Jupyter notebook from your local environment to Amazon SageMaker. Learn how to automate repository and package operations. Using script mode, you also learn how to migrate your code to built-in algorithms and frameworks in order to easily train and deploy at any scale on managed infrastructure. Builders Session Julien Simon
AIM319-R1 - [REPEAT 1] Amazon SageMaker: Use prebuilt Jupyter notebooks In this builders session, we show you how to bring an existing Jupyter notebook from your local environment to Amazon SageMaker. Learn how to automate repository and package operations. Using script mode, you also learn how to migrate your code to built-in algorithms and frameworks in order to easily train and deploy at any scale on managed infrastructure. Builders Session Julien Simon
AIM319-R2 - [REPEAT 2] Amazon SageMaker: Use prebuilt Jupyter notebooks In this builders session, we show you how to bring an existing Jupyter notebook from your local environment to Amazon SageMaker. Learn how to automate repository and package operations. Using script mode, you also learn how to migrate your code to built-in algorithms and frameworks in order to easily train and deploy at any scale on managed infrastructure. Builders Session Julien Simon
AIM320-R - [REPEAT] Amazon SageMaker Ground Truth: Create a data labeling workflow Amazon SageMaker Ground Truth helps you build and manage highly accurate training datasets quickly. Ground Truth offers easy access to public and private human labelers and provides them with prebuilt workflows and interfaces for common labeling tasks. During this builders session, we show you how to start and use a workflow. Builders Session Bill Verthein
AIM320-R1 - [REPEAT 1] Amazon SageMaker Ground Truth: Create a data labeling workflow Amazon SageMaker Ground Truth helps you build and manage highly accurate training datasets quickly. Ground Truth offers easy access to public and private human labelers and provides them with prebuilt workflows and interfaces for common labeling tasks. During this builders session, we show you how to start and use a workflow. Builders Session Bill Verthein
AIM322-R - [REPEAT] Fraud: How to detect and prevent it using ML Looking to protect your company from anonymous activity and prevent bad-actor behavior? This session details how to implement a customized fraud detection and prevention solution using machine learning services, how to proactively identify these use cases, and how to implement changes to protect your enterprise and your customers. Session Ryan Schmiedl Nick Tostenrude
AIM322-R1 - [REPEAT 1] Fraud: How to detect and prevent it using ML Looking to protect your company from anonymous activity and prevent bad-actor behavior? This session details how to implement a customized fraud detection and prevention solution using machine learning services, how to proactively identify these use cases, and how to implement changes to protect your enterprise and your customers. Session Ryan Schmiedl Nick Tostenrude
AIM323 - Delight your customers with ML-based personalized recommendations Recommendation engines make targeted marketing campaigns, re-ranking of items, personalized notifications, and personalized search possible. In this session, we deep-dive into using Amazon Personalize to create and manage personalized recommendations efficiently, letting you focus on the real value of the data for your business. We discover how these deep learning techniques have a direct impact on the bottom line of your business by increasing engagement, click-through, satisfaction, and revenue. Learn from customer examples and dive into some live demonstrations. Session Vaibhav Sethi Robin Mizreh Aymeric ROFFE
AIM326-R - [REPEAT] Implement ML workflows with Kubernetes and Amazon SageMaker Until recently, data scientists have spent much time performing operational tasks, such as ensuring that frameworks, runtimes, and drivers for CPUs and GPUs work well together. In addition, data scientists needed to design and build end-to-end machine learning (ML) pipelines to orchestrate complex ML workflows for deploying ML models in production. With Amazon SageMaker, data scientists can now focus on creating the best possible models while enabling organizations to easily build and automate end-to-end ML pipelines. In this session, we dive deep into Amazon SageMaker and container technologies, and we discuss how easy it is to integrate such tasks as model training and deployment into Kubernetes and Kubeflow-based ML pipelines. Session Aditya Bindal David Ping
AIM326-R1 - [REPEAT 1] Implement ML workflows with Kubernetes and Amazon SageMaker Until recently, data scientists have spent much time performing operational tasks, such as ensuring that frameworks, runtimes, and drivers for CPUs and GPUs work well together. In addition, data scientists needed to design and build end-to-end machine learning (ML) pipelines to orchestrate complex ML workflows for deploying ML models in production. With Amazon SageMaker, data scientists can now focus on creating the best possible models while enabling organizations to easily build and automate end-to-end ML pipelines. In this session, we dive deep into Amazon SageMaker and container technologies, and we discuss how easy it is to integrate such tasks as model training and deployment into Kubernetes and Kubeflow-based ML pipelines. Session Aditya Bindal David Ping
AIM327 - Security for ML environments with Amazon SageMaker, featuring Vanguard Amazon SageMaker is a modular, fully managed platform that enables developers and data scientists to quickly and easily build, train, and deploy machine learning models at any scale. In this session, we dive deep into the security configurations of Amazon SageMaker components, including notebooks, training, and hosting endpoints. A representative from Vanguard joins us to discuss the company’s use of Amazon SageMaker and its implementation of key controls in a highly regulated environment, including fine-grained access control, end-to-end encryption in transit, encryption at rest with customer master keys (CMKs), private connectivity to all Amazon SageMaker API operations, and comprehensive audit trails for resource and data access. If you want to build secure ML environments, this session is for you.     Session Ilya Epshteyn Ritesh Shah
AIM328 - Build predictive maintenance systems with Amazon SageMaker Across a wide spectrum of industries, customers are starting to utilize prediction maintenance models to proactively fix problems before they impact production. The result is an optimized supply chain and improved working conditions. In this session, learn how to use data from equipment to build, train, and deploy predictive models. We dive deep into the architecture for using the turbofan degradation simulation dataset to train the model to recognize potential equipment failures and also how to provide recommended actions. Finally, we walk through an AWS CloudFormation template so you can get started quickly. Chalk Talk Laith Al-Saadoon Emily Webber
AIM329 - Using deep learning to track wildfires and air quality ALERTWildfire is a camera-based network infrastructure that captures satellite imagery of wildfires. In this chalk talk, we discuss deep-learning techniques that use this satellite imagery along with meteorological data to track wildfires and predict air quality in real time. Chalk Talk Sanjay Padhi Feng Yan
AIM330 - Build custom data labeling workflows with Amazon SageMaker In this chalk talk, we explain how to use customer pre- and post-Lambda functions to extend the functionality of Amazon SageMaker Ground Truth. We show you how to make a custom annotator UI and use AWS Lambda to provide custom pre- and post-processing of annotations. Chalk Talk Anjan Dash Hareesh Lakshmi Narayanan
AIM331-R - [REPEAT] Choose the proper algorithm in Amazon SageMaker Amazon SageMaker gives you choices for the best algorithm to use to train your model. You get a 10x improvement in algorithm performance when using one of the build-in algorithms with Amazon SageMaker. However, it can be confusing to pick between the options. Commonly used ML algorithms are built-in and there are over 200 additional pre-trained models and algorithms available in AWS Marketplace. Plus you can also bring any other algorithm or framework by building it into a Docker container. During this chalk talk, we help you make sense of these choices to optimize performance. Chalk Talk Laurence Rouesnel Brad Kenstler
AIM331-R1 - [REPEAT 1] Choose the proper algorithm in Amazon SageMaker Amazon SageMaker gives you choices for the best algorithm to use to train your model. You get a 10x improvement in algorithm performance when using one of the build-in algorithms with Amazon SageMaker. However, it can be confusing to pick between the options. Commonly used ML algorithms are built-in and there are over 200 additional pre-trained models and algorithms available in AWS Marketplace. Plus you can also bring any other algorithm or framework by building it into a Docker container. During this chalk talk, we help you make sense of these choices to optimize performance. Chalk Talk Laurence Rouesnel Brad Kenstler
AIM333 - How to design high-quality data-labeling pipelines Amazon SageMaker Ground Truth is a fully managed service for data labeling. In this chalk talk, we explore the tools and techniques available in Ground Truth to help generate high-quality labels, from audit and verification workflows to annotation consolidation and active learning. We also discuss how the structured output format lends itself to generating hierarchical taxonomies of data. Chalk Talk Jonathan Buck Fedor Zhdanov
AIM334-R - [REPEAT] Preparing data for use in AutoML scenarios AutoML takes care of the heavy lifting of selecting the most optimal algorithm, but as the saying goes "garbage in, garbage out." Prepping data for use in AutoML scenarios is one of the most challenging components, and the most prohibitive to a successful proof of concept. Join us to discuss best practices for data prep, and walk through examples of how to do this for sample datasets. Chalk Talk Hussain Karimi
AIM334-R1 - [REPEAT 1] Preparing data for use in AutoML scenarios AutoML takes care of the heavy lifting of selecting the most optimal algorithm, but as the saying goes "garbage in, garbage out." Prepping data for use in AutoML scenarios is one of the most challenging components, and the most prohibitive to a successful proof of concept. Join us to discuss best practices for data prep, and walk through examples of how to do this for sample datasets. Chalk Talk Hussain Karimi
AIM335-R1 - [REPEAT 1] Accelerate time-series forecasting with Amazon Forecast Based on the same technology used at Amazon.com, Amazon Forecast uses machine learning to combine time-series data with additional variables to build up to 50% more accurate forecasts. In this workshop, prepare a dataset, build models based on that dataset, evaluate a model's performance based on real observations, and learn how to evaluate the value of a forecast compared with another. Gain the skills to make decisions that will impact the bottom line of your business. Workshop Gunjan Garg Eric Greene
AIM337-R - [REPEAT] Deep dive into Amazon SageMaker security features Customers manage highly sensitive data on behalf of their clients and customers. To apply machine learning techniques to highly sensitive data, they must maintain a high security bar to guard against data exfiltration or abuse of sensitive datasets. Join us for this chalk talk as we dive into the many features of Amazon SageMaker that enable customers to build highly secure data science environments and support stringent security requirements. Chalk Talk Dave Walker Jason Barto
AIM337-R1 - [REPEAT 1] Deep dive into Amazon SageMaker security features Customers manage highly sensitive data on behalf of their clients and customers. To apply machine learning techniques to highly sensitive data, they must maintain a high security bar to guard against data exfiltration or abuse of sensitive datasets. Join us for this chalk talk as we dive into the many features of Amazon SageMaker that enable customers to build highly secure data science environments and support stringent security requirements. Chalk Talk Jason Barto Dave Walker
AIM338 - Machine learning with containers and Amazon SageMaker Data scientists and machine learning engineers use containers to create custom, lightweight environments to train and serve models at scale with deep learning frameworks, such as TensorFlow, Apache MXNet, and PyTorch, achieving consistency across development and deployment. In this chalk talk, we discuss how to use AWS Deep Learning Containers to train and serve models with Amazon SageMaker. Chalk Talk Indu Thangakrishnan Shashank Prasanna
AIM340-R - [REPEAT] Next-gen video: Transcription, translation & search, powered by ML Come discuss how machine learning can enhance your video files and generate searchable metadata in this chalk talk. The Media Analysis Solution on AWS uses Amazon Rekognition for facial recognition, Amazon Transcribe to create transcripts, Amazon Comprehend to run sentiment analysis on the transcripts, and Amazon Translate to make content available in multiple languages. By the end of this session, you will know how to upload your media files and work with the metadata that is automatically extracted through these services. Chalk Talk Watson Srivathsan Priyank Goyal
AIM340-R1 - [REPEAT 1] Next-gen video: Transcription, translation & search, powered by ML Come discuss how machine learning can enhance your video files and generate searchable metadata in this chalk talk. The Media Analysis Solution on AWS uses Amazon Rekognition for facial recognition, Amazon Transcribe to create transcripts, Amazon Comprehend to run sentiment analysis on the transcripts, and Amazon Translate to make content available in multiple languages. By the end of this session, you will know how to upload your media files and work with the metadata that is automatically extracted through these services. Chalk Talk Watson Srivathsan Priyank Goyal
AIM341 - Deep learning on graphs Graph databases are being adopted in a wide range of business domains and can be used with deep learning to tackle many common business problems. In this chalk talk, we explain how to do deep learning on graphs with Amazon SageMaker. We explore three use cases, including how to detect fraudulent accounts on social networks, how to identify social groups for marketing, and how to judge the creditworthiness of individuals. Chalk Talk Balaji Kamakoti VEBHHAV SINGH
AIM342-R - [REPEAT] Large-scale document processing with Amazon Textract Millions of mortgage applications and hundreds of millions of W-2 tax forms are processed each year—many times using manual data entry. In this chalk talk, we discuss how to architect a solution to extract text and data from these types of documents at scale for automatic processing. Learn how to build a serverless, highly available, highly scalable architecture that can easily handle spiky workloads. Chalk Talk Kashif Imran
AIM342-R1 - [REPEAT 1] Large-scale document processing with Amazon Textract Millions of mortgage applications and hundreds of millions of W-2 tax forms are processed each year—many times using manual data entry. In this chalk talk, we discuss how to architect a solution to extract text and data from these types of documents at scale for automatic processing. Learn how to build a serverless, highly available, highly scalable architecture that can easily handle spiky workloads. Chalk Talk Kashif Imran
AIM343-R - [REPEAT] Build computer vision models with Amazon SageMaker Implementing computer vision (CV) models just got simpler and faster. In this chalk talk, learn how to implement CV models using Apache MXNet and the Gluon CV Toolkit, which provide implementations of state-of-the-art deep learning algorithms in computer vision to help engineers, researchers, and students quickly prototype products, validate new ideas, and learn computer vision. Chalk Talk Nathalie Rauschmayr
AIM343-R1 - [REPEAT 1] Build computer vision models with Amazon SageMaker Implementing computer vision (CV) models just got simpler and faster. In this chalk talk, learn how to implement CV models using Apache MXNet and the Gluon CV Toolkit, which provide implementations of state-of-the-art deep learning algorithms in computer vision to help engineers, researchers, and students quickly prototype products, validate new ideas, and learn computer vision. Chalk Talk Nathalie Rauschmayr
AIM344-R - [REPEAT] Crafting a conversational platform strategy In this chalk talk, we discuss how to build an Amazon Lex chatbot that can conduct a conversation based on data in a sample business intelligence database. We then explore ways that this chatbot could be adapted to your own datasets. Chalk Talk Anubhav Mishra Brian Yost
AIM344-R1 - [REPEAT 1] Crafting a conversational platform strategy In this chalk talk, we discuss how to build an Amazon Lex chatbot that can conduct a conversation based on data in a sample business intelligence database. We then explore ways that this chatbot could be adapted to your own datasets. Chalk Talk Anubhav Mishra Brian Yost
AIM345 - Build accurate models with automatic model tuning In many cases, what separates good models from great ones is the choice of hyperparameters. For example, how many layers you should use? What should the learning rate be? And what should the regularization parameters be? In this chalk talk, we dive deep into the automatic model tuning feature of Amazon SageMaker. Automatic model tuning lets you skip the tedious trial-and-error process of manually adjusting model parameters and instead performs hyperparameter optimization by discovering interesting features in your data and learning how those features interact to affect accuracy. You save days or even weeks of time. Chalk Talk Cyrus Vahid
AIM346-R - [REPEAT] Personalized user engagement with machine learning In this chalk talk, we discuss how to use Amazon Personalize and Amazon Pinpoint to provide a personalized, omni-channel experience starting in your mobile application. We discuss best practices for real-time updates, personalized notifications (push), and messaging (email and text) that drives user engagement and product discovery. We also demonstrate how other mobile services can be used to facilitate rapid prototyping. Chalk Talk John Burry Mav Peri
AIM346-R1 - [REPEAT 1] Personalized user engagement with machine learning In this chalk talk, we discuss how to use Amazon Personalize and Amazon Pinpoint to provide a personalized, omni-channel experience starting in your mobile application. We discuss best practices for real-time updates, personalized notifications (push), and messaging (email and text) that drives user engagement and product discovery. We also demonstrate how other mobile services can be used to facilitate rapid prototyping. Chalk Talk John Burry Mav Peri
AIM347 - Time-series prediction using GluonTS and Amazon SageMaker Time-series prediction—whether it is regression, classification, or anomaly detection—has experienced a renaissance in the past three years thanks to the application of neural models. In turn, AWS has released an open-source Gluon-based toolkit, GluonTS, for time-series prediction. In this session we provide you with different models that are implemented as part of GluonTS. We also provide guidance as to where and how to apply each model. Workshop Nathalie Rauschmayr Shashank Prasanna
AIM348 - Deploying and managing machine learning models at scale In this workshop, we dive into the deploy module of Amazon SageMaker. Amazon SageMaker offers one-click deployment onto auto-scaling Amazon ML instances across multiple Availability Zones. We explain how Amazon SageMaker manages your production compute infrastructure on your behalf to perform health checks, apply security patches, and conduct other routine maintenance. Then we explore the batch transform feature, which enables you to run predictions on large or small batch data. Finally, we explore inference pipelines, which let you pass raw input data and execute preprocessing, predictions, and post-processing. After the workshop, you will be ready to scale ML. Workshop Sireesha Muppala Urvashi Chowdhary
AIM349 - Build a hotel recommender with Amazon Personalize—no ML skills needed Recommender systems are everywhere. Many successful e-commerce companies leverage personalized recommendations to help their customers discover new products, find the right product when they need it, discover similar products, and more. In the industry of travel, companies want to inspire travelers with new hotels or find similar hotels based on their preferences. You don't need to be an ML expert to build such a recommendation engine. In this chalk talk, learn how to easily build and deploy a model using state-of-the-art techniques with Amazon Personalize. Chalk Talk Antonio Rodriguez Pavlos Mitsoulis Ntompos
AIM350-R - [REPEAT] Identifying product mentions in customer reviews using ML In recent years, we have seen the ascent of conversational AI, the rise of chatbots, and an exhaustive amount of data from customer calls, emails, and Tweets. Natural language processing (NLP) is at the core of all of these innovations. In this hands-on session, learn how Amazon Comprehend, and NLP service, enables you to train your own custom-named entity without needing to be skilled in machine learning (ML). Learn how to group support emails by department, social media posts by product, and analyst reports by business unit. Builders Session Phi Nguyen
AIM350-R1 - [REPEAT 1] Identifying product mentions in customer reviews using ML In recent years, we have seen the ascent of conversational AI, the rise of chatbots, and an exhaustive amount of data from customer calls, emails, and Tweets. Natural language processing (NLP) is at the core of all of these innovations. In this hands-on session, learn how Amazon Comprehend, and NLP service, enables you to train your own custom-named entity without needing to be skilled in machine learning (ML). Learn how to group support emails by department, social media posts by product, and analyst reports by business unit. Builders Session Phi Nguyen
AIM351-R - [REPEAT] Build a smart search experience for document images and PDFs Documents are a primary tool for record keeping, communication, collaboration, and transactions across many industries and sectors, including Financial, Healthcare, Legal, and Real Estate. By extracting structured data from documents, you can create a smart search experience and quickly search through millions of documents. In this session, you learn how to build a smart index using Amazon Textract to search across and within documents. Builders Session Basit Hussain
AIM351-R1 - [REPEAT 1] Build a smart search experience for document images and PDFs Documents are a primary tool for record keeping, communication, collaboration, and transactions across many industries and sectors, including Financial, Healthcare, Legal, and Real Estate. By extracting structured data from documents, you can create a smart search experience and quickly search through millions of documents. In this session, you learn how to build a smart index using Amazon Textract to search across and within documents. Builders Session Basit Hussain
AIM353-R - [REPEAT] Identify and mask health data in images or text Many companies in the Healthcare industry generate large amounts of data that’s used in a variety of applications, such as population health management and electronic health records. Developers need to find ways to use the valuable health-related data in these applications while meeting their compliance obligations around sensitive data, such as protected health information (PHI). Join us in this builders session to learn how to use a pre-built solution from AWS, AI-Powered Health Data Masking, to identify and mask health-related data in images or text. Builders Session James Wiggins
AIM353-R1 - [REPEAT 1] Identify and mask health data in images or text Many companies in the Healthcare industry generate large amounts of data that’s used in a variety of applications, such as population health management and electronic health records. Developers need to find ways to use the valuable health-related data in these applications while meeting their compliance obligations around sensitive data, such as protected health information (PHI). Join us in this builders session to learn how to use a pre-built solution from AWS, AI-Powered Health Data Masking, to identify and mask health-related data in images or text. Builders Session Aaron Friedman
AIM354-R - [REPEAT] Build a conversational 3D avatar In this session, you learn how to combine AI services with AR/VR to build 3D interactive experiences. You use Amazon Sumerian to build a 3D avatar that integrates into Amazon Lex and Amazon Polly to drive a "how-to” based natural conversation. At the end of this session, you'll have the skills you need to expand and build your own interactive conversational experiences. Builders Session Will Cannady
AIM354-R1 - [REPEAT 1] Build a conversational 3D avatar In this session, you learn how to combine AI services with AR/VR to build 3D interactive experiences. You use Amazon Sumerian to build a 3D avatar that integrates into Amazon Lex and Amazon Polly to drive a "how-to” based natural conversation. At the end of this session, you'll have the skills you need to expand and build your own interactive conversational experiences. Builders Session Will Cannady
AIM355-R - [REPEAT] Automate creation of redacted content with the Media Analysis Solution Performing content moderation on media assets is a time-consuming and often costly task. This session explains how to build a highly efficient automated content moderation workflow to create redacted versions of your media assets by utilizing AWS Media Services and machine learning incorporated with the Media Analysis Solution. Learn how to deploy a serverless architecture to run ML analysis on your media and perform redaction that fits your business or compliance requirements, such as the blurring of faces or logos, redaction of user-defined keywords in audio or text, or even labeling of media that contains moderated content like violence or graphic activities. Builders Session Brandon Dold
AIM355-R1 - [REPEAT 1] Automate creation of redacted content with the Media Analysis Solution Performing content moderation on media assets is a time-consuming and often costly task. This session explains how to build a highly efficient automated content moderation workflow to create redacted versions of your media assets by utilizing AWS Media Services and machine learning incorporated with the Media Analysis Solution. Learn how to deploy a serverless architecture to run ML analysis on your media and perform redaction that fits your business or compliance requirements, such as the blurring of faces or logos, redaction of user-defined keywords in audio or text, or even labeling of media that contains moderated content like violence or graphic activities. Builders Session Brandon Dold
AIM356-R - [REPEAT] Smarter text analytics with Amazon ES & Amazon Comprehend In this session, learn how to use Amazon Elasticsearch Service (Amazon ES) and Amazon Comprehend to extract and visualize insights from text. Learn how to index and analyze news and Twitter feeds, and create live dashboards to visualize extracted entities, key phrases, and sentiment. Builders Session Dimitris Soulios
AIM356-R1 - [REPEAT 1] Smarter text analytics with Amazon ES & Amazon Comprehend In this session, learn how to use Amazon Elasticsearch Service (Amazon ES) and Amazon Comprehend to extract and visualize insights from text. Learn how to index and analyze news and Twitter feeds, and create live dashboards to visualize extracted entities, key phrases, and sentiment. Builders Session Dimitris Soulios
AIM357 - Build an ETL pipeline to analyze customer data Machine learning involves more than just training models; you need to source and prepare data, engineer features, select algorithms, train and tune models, and then deploy those models and monitor their performance in production. Learn how to set up an ETL pipeline to analyze customer data using Amazon SageMaker, AWS Glue, and AWS Step Functions. Workshop Ben Snively Kieran Kavanagh
AIM358 - Prepare data for ML using Amazon SageMaker High-quality datasets are the foundation of machine learning. In this chalk talk, we explain how to use Amazon SageMaker to prepare data. We show you how to create data inference pipelines so you can pass raw input data and execute preprocessing, predictions, and post-processing on real-time and batch inference requests. We also show you how to build data processing and feature engineering pipelines with a suite of feature transformers available in the SparkML and Scikit-learn framework containers in Amazon SageMaker. Chalk Talk Christian Williams
AIM359-R - [REPEAT] Build a fraud detection system with Amazon SageMaker In this workshop, we will explore the new AWS Fraud Detection Solution. We show you how to build, train, and deploy a fraud detection machine learning model. The fraud detection model recognizes fraud patterns, and is self-learning which enables it to adapt to new, unknown fraud patterns. We will show you how to execute automated transaction processing, and how to the Fraud Detection solution flags that activity for review. The solution comes with an implementation guide and accompanying AWS CloudFormation template. Workshop Sergey Ermolin VEBHHAV SINGH Vebhnonohav Singhnah
AIM359-R1 - [REPEAT 1] Build a fraud detection system with Amazon SageMaker In this workshop, we will explore the new AWS Fraud Detection Solution. We show you how to build, train, and deploy a fraud detection machine learning model. The fraud detection model recognizes fraud patterns, and is self-learning which enables it to adapt to new, unknown fraud patterns. We will show you how to execute automated transaction processing, and how to the Fraud Detection solution flags that activity for review. The solution comes with an implementation guide and accompanying AWS CloudFormation template. Workshop Sergey Ermolin VEBHHAV SINGH Vebhnonohav Singhnah
AIM360 - Build a predictive maintenance system with Amazon SageMaker In this workshop, we explore the new AWS Predictive Maintenance Using Machine Learning solution. This solution deploys a machine learning model and an example dataset of turbofan degradation simulation data to train the model to recognize potential equipment failures. You can use this solution to automate the detection of potential equipment failures and provide recommended actions to take. We walk through the solution’s implementation guide and accompanying AWS CloudFormation template. Workshop Laith Al-Saadoon Emily Webber
AIM365-R - [REPEAT] Build a custom model for object and logo detection In this discussion, we look at how you can use machine learning to automatically detect your logo or product, allowing you to track where your assets are being seen and used. Explore how this capability empowers marketers and decision makers with data on impressions, digital brand engagement, and the online tracking of their assets. Chalk Talk Rahul Bhotika Kashif Imran
AIM365-R1 - [REPEAT 1] Build a custom model for object and logo detection In this discussion, we look at how you can use machine learning to automatically detect your logo or product, allowing you to track where your assets are being seen and used. Explore how this capability empowers marketers and decision makers with data on impressions, digital brand engagement, and the online tracking of their assets. Chalk Talk Rahul Bhotika Kashif Imran
AIM365-R2 - [REPEAT 2] Build a custom model for object and logo detection In this discussion, we look at how you can use machine learning to automatically detect your logo or product, allowing you to track where your assets are being seen and used. Explore how this capability empowers marketers and decision makers with data on impressions, digital brand engagement, and the online tracking of their assets. Chalk Talk Kashif Imran Rahul Bhotika
AIM366 - Experience the real-world ML lifecycle with Amazon SageMaker In this workshop, you get hands-on experience taking custom machine learning (ML) solutions from prototype to production. You use Amazon SageMaker to build, train, and deploy ML models for a real-world Amazon Robotics use case. You learn about the human-robot interactions that happen hundreds of times every second to power the Amazon fulfillment network. You craft your own ML models based on millions of anonymized data points, and you deploy your models to serve warehouses across the globe with regional endpoints that scale automatically. Workshop Mike Calder Rick Nayar
AIM366-R - [REPEAT] SpaceNet: ML to solve mapping challenges SpaceNet, a nonprofit LLC focusing on solving geospatial problems such as mapping road network routes after a natural disaster, has open-sourced more than 6,500 square kilometers of high-resolution satellite imagery with approximately 800,000 building footprint labels and 8,000 square kilometers of road network labels. Join us for a discussion on how to use this data to train machine learning algorithms that help disseminate timely information in the aftermath of natural disasters. Chalk Talk Kate Werling Joe Flasher Ryan Lewis
AIM366-R1 - [REPEAT 1] SpaceNet: ML to solve mapping challenges SpaceNet, a nonprofit LLC focusing on solving geospatial problems such as mapping road network routes after a natural disaster, has open-sourced more than 6,500 square kilometers of high-resolution satellite imagery with approximately 800,000 building footprint labels and 8,000 square kilometers of road network labels. Join us for a discussion on how to use this data to train machine learning algorithms that help disseminate timely information in the aftermath of natural disasters. Chalk Talk Kate Werling Joe Flasher Ryan Lewis
AIM367-S - Data is out, knowing is in: Applying AI to automate cloud operations With firefighting, manual operations, and troubleshooting, it is an exciting time to monitor applications in the cloud. In this session, renowned DevOps and digital evangelists Andi Grabner and Dave Anderson provide practical advice on how to save time monitoring your cloud applications. Learn how to automate your operations, use AI for assisted intelligence, and enable complete automation. In addition, learn about auto-remediation and how to always know the status of your applications, no matter how complex your hybrid cloud. Also hear from one customer about how a vision can become a reality. This presentation is brought to you by Dynatrace, an APN Partner. Session Andreas Grabner Anderson David
AIM401-R - [REPEAT] Distributed training, tuning, and inference with TensorFlow in Amazon SageMaker The TensorFlow deep learning framework is widely used in academia and industry. Using Amazon SageMaker, organizations can quickly begin a fully managed TensorFlow experience. In this workshop, we train and deploy TensorFlow models using key Amazon SageMaker features for an efficient workflow. Specifically, we prototype training and inference code locally before moving to full-scale training and production deployment; compare and contrast Amazon SageMaker’s support for distributed training with parameter servers and Horovod; apply automatic model tuning to improve TensorFlow models; and make predictions in production using either real-time endpoints backed by TensorFlow Serving or highly performant batch transform jobs at scale. Workshop Brent Rabowsky Rama Thamman
AIM401-R1 - [REPEAT 1] Distributed training, tuning, and inference with TensorFlow in Amazon SageMaker The TensorFlow deep learning framework is widely used in academia and industry. Using Amazon SageMaker, organizations can quickly begin a fully managed TensorFlow experience. In this workshop, we train and deploy TensorFlow models using key Amazon SageMaker features for an efficient workflow. Specifically, we prototype training and inference code locally before moving to full-scale training and production deployment; compare and contrast Amazon SageMaker’s support for distributed training with parameter servers and Horovod; apply automatic model tuning to improve TensorFlow models; and make predictions in production using either real-time endpoints backed by TensorFlow Serving or highly performant batch transform jobs at scale. Workshop Brent Rabowsky Rama Thamman
AIM402-R - [REPEAT] Deep learning with PyTorch PyTorch is a deep-learning framework that is becoming popular, especially for rapid prototyping of new models. You can get started easily with PyTorch using Amazon SageMaker, a fully managed service, to build, train, and deploy machine learning models at scale. In this workshop, we build a natural-language-processing model to analyze text. Workshop Chaitanya Hazarey Kris Skrinak
AIM402-R1 - [REPEAT 1] Deep learning with PyTorch PyTorch is a deep-learning framework that is becoming popular, especially for rapid prototyping of new models. You can get started easily with PyTorch using Amazon SageMaker, a fully managed service, to build, train, and deploy machine learning models at scale. In this workshop, we build a natural-language-processing model to analyze text. Workshop Kris Skrinak Chaitanya Hazarey
AIM403-R - [REPEAT] Deep learning with Apache MXNet In this workshop, learn how to get started with the Apache MXNet deep learning framework using Amazon SageMaker, a fully managed service, to build, train, and deploy machine learning models at scale. Learn how to build a computer-vision model using MXNet to extract insights from an image dataset. Once the model is built, learn how to quickly train it to get the best possible results and then easily deploy it to production using Amazon SageMaker. Workshop Thom Lane Thomas Delteil
AIM403-R1 - [REPEAT 1] Deep learning with Apache MXNet In this workshop, learn how to get started with the Apache MXNet deep learning framework using Amazon SageMaker, a fully managed service, to build, train, and deploy machine learning models at scale. Learn how to build a computer-vision model using MXNet to extract insights from an image dataset. Once the model is built, learn how to quickly train it to get the best possible results and then easily deploy it to production using Amazon SageMaker. Workshop Thomas Delteil Thom Lane
AIM404-R - [REPEAT] Amazon SageMaker RL: Solving business problems with RL and bandits In reinforcement learning (RL), an RL agent learns in an interactive environment by trial and error using feedback from its own actions, and can make sophisticated multi-step decisions. As a result, RL has broad applicability in robotics, industrial control, finance, HVAC, dialog systems, online advertising, and more. This workshop provides practitioners with hands-on experience building and deploying RL agents from scratch. We use examples from two scenarios: one where the environment can be simulated (computer games, resource allocation simulators, etc.) and one where it cannot be and the agent learns in a live environment (recommender systems, trading bots, etc.). Workshop Girish Dilip Patil Marc Cabocel
AIM404-R1 - [REPEAT 1] Amazon SageMaker RL: Solving business problems with RL and bandits In reinforcement learning (RL), an RL agent learns in an interactive environment by trial and error using feedback from its own actions, and can make sophisticated multi-step decisions. As a result, RL has broad applicability in robotics, industrial control, finance, HVAC, dialog systems, online advertising, and more. This workshop provides practitioners with hands-on experience building and deploying RL agents from scratch. We use examples from two scenarios: one where the environment can be simulated (computer games, resource allocation simulators, etc.) and one where it cannot be and the agent learns in a live environment (recommender systems, trading bots, etc.).     Workshop Marc Cabocel Girish Dilip Patil
AIM405 - Optimize deep learning models for edge deployments with AWS DeepLens In this workshop, learn how to optimize your computer vision pipelines for edge deployments with AWS DeepLens and Amazon SageMaker Neo. Also learn how to build a sample object detection model with Amazon SageMaker and deploy it to AWS DeepLens. Finally, learn how to optimize your deep learning models and code to achieve faster performance for use cases where speed matters. Workshop Nathaniel Slater Phu Nguyen
AIM406-R - [REPEAT] Amazon SageMaker and Apache MXNet: Tips & tricks The Apache MXNet deep learning framework is used for developing, training, and deploying diverse AI applications, including computer vision, speech recognition, and natural language processing. In this builders session, learn how to build, train, and deploy deep learning models with MXNet in Amazon SageMaker, a fully managed service that makes it easy to develop machine learning applications. Builders Session Haibin Lin
AIM406-R1 - [REPEAT 1] Amazon SageMaker and Apache MXNet: Tips & tricks The Apache MXNet deep learning framework is used for developing, training, and deploying diverse AI applications, including computer vision, speech recognition, and natural language processing. In this builders session, learn how to build, train, and deploy deep learning models with MXNet in Amazon SageMaker, a fully managed service that makes it easy to develop machine learning applications. Builders Session Haibin Lin
AIM407-R - [REPEAT] Amazon SageMaker and PyTorch: Tips & tricks With support for PyTorch in Amazon SageMaker, you have a flexible deep learning framework combined with a fully managed machine learning solution to transition seamlessly from research prototyping to production deployment. In this builders session, learn how to build, train, and deploy PyTorch deep learning models in Amazon SageMaker. Builders Session Charles Frenzel
AIM407-R1 - [REPEAT 1] Amazon SageMaker and PyTorch: Tips & tricks With support for PyTorch in Amazon SageMaker, you have a flexible deep learning framework combined with a fully managed machine learning solution to transition seamlessly from research prototyping to production deployment. In this builders session, learn how to build, train, and deploy PyTorch deep learning models in Amazon SageMaker. Builders Session Charles Frenzel
AIM408-R - [REPEAT] Amazon SageMaker and TensorFlow: Tips & tricks TensorFlow is one of several open-source deep learning frameworks used in machine learning development that is currently popular among developers. In this builders session, learn how to build, train, and deploy deep learning models with TensorFlow in Amazon SageMaker, a fully managed service that makes it easy to develop machine learning applications. Builders Session Mark Roy
AIM408-R1 - [REPEAT 1] Amazon SageMaker and TensorFlow: Tips & tricks TensorFlow is one of several open-source deep learning frameworks used in machine learning development that is currently popular among developers. In this builders session, learn how to build, train, and deploy deep learning models with TensorFlow in Amazon SageMaker, a fully managed service that makes it easy to develop machine learning applications. Builders Session Mark Roy
AIM408-R2 - [REPEAT 2] Amazon SageMaker and TensorFlow: Tips & tricks TensorFlow is one of several open-source deep learning frameworks used in machine learning development that is currently popular among developers. In this builders session, learn how to build, train, and deploy deep learning models with TensorFlow in Amazon SageMaker, a fully managed service that makes it easy to develop machine learning applications. Builders Session Brent Rabowsky
AIM409-R - [REPEAT] Amazon SageMaker: Bring your own framework In this builders session, we show you how to set up your own machine learning environments and workflows on Amazon SageMaker together with AWS Deep Learning AMIs. First we explain how to use the prepackaged, optimized Amazon Machine Images (AMIs). Then we show you how to use these custom environments on Amazon SageMaker using AWS Deep Learning Containers, which provide Docker images preinstalled and tested with popular deep learning frameworks, so you can skip the complicated process of building and optimizing your environments from scratch. Come away understanding how to integrate custom algorithms into Amazon SageMaker. Builders Session Shashank Prasanna
AIM409-R1 - [REPEAT 1] Amazon SageMaker: Bring your own framework In this builders session, we show you how to set up your own machine learning environments and workflows on Amazon SageMaker together with AWS Deep Learning AMIs. First we explain how to use the prepackaged, optimized Amazon Machine Images (AMIs). Then we show you how to use these custom environments on Amazon SageMaker using AWS Deep Learning Containers, which provide Docker images preinstalled and tested with popular deep learning frameworks, so you can skip the complicated process of building and optimizing your environments from scratch. Come away understanding how to integrate custom algorithms into Amazon SageMaker. Builders Session Shashank Prasanna
AIM410-R - [REPEAT] Deep learning applications with TensorFlow, featuring Mobileye TensorFlow is one of several open-source deep learning frameworks used in machine learning development that is currently popular among developers. But it can be challenging to scale TensorFlow model training and inference. Amazon SageMaker provides several features that solve these challenges. In this session, learn about these features, including distributed training, cost-effective inference, and workflow management. Then, hear from Mobileye, an Intel company focused on developing and delivering driving assist and autonomous vehicles solutions, about how they migrated their training workloads to Amazon SageMaker to reduce development cycle time from weeks to days. Session Julien Simon Zdravko Pantic Chaim Rand
AIM410-R1 - [REPEAT 1] Deep learning applications with TensorFlow, featuring Fannie Mae TensorFlow is one of several currently popular open-source deep learning frameworks used in machine learning development. But it can be challenging to scale TensorFlow model training and inference. Amazon SageMaker provides several features that solve these challenges. In this session, learn about these features, including distributed training, cost-effective inference, and workflow management. Then, hear from Fannie Mae about how it developed its TensorFlow-based home appraisal models using Amazon SageMaker for scalability, security, and ease of management. Session Julien Simon Vindhan Sahayam Bin Lu
AIM411-R - [REPEAT] Deep learning applications using Apache MXNet The Apache MXNet deep learning framework is used for developing, training, and deploying diverse AI applications, including computer vision, speech recognition, and natural language processing (NLP). In this session, learn how to get started with MXNet on Amazon SageMaker. See how to build computer vision and NLP models using MXNet to automatically extract information from paper documents, such as expense receipts, and populate data records. Session Thom Lane Neil Delargy Ben Fields
AIM411-R1 - [REPEAT 1] Deep learning applications using Apache MXNet The Apache MXNet deep learning framework is used for developing, training, and deploying diverse AI applications, including computer vision, speech recognition, and natural language processing (NLP). In this session, learn how to get started with MXNet on Amazon SageMaker. See how to build computer vision and NLP models using MXNet to automatically extract information from paper documents, such as expense receipts, and populate data records. Session Thom Lane Neil Delargy Ben Fields
AIM412-R - [REPEAT] Deep learning applications using PyTorch, featuring Autodesk With support for PyTorch in Amazon SageMaker, you have a flexible deep learning framework combined with a fully managed machine learning solution to transition seamlessly from research prototyping to production deployment. In this session, hear from the PyTorch team on the latest features and library releases. Also learn how to develop with PyTorch using Amazon SageMaker for key use cases such as using a BERT model for natural language processing (NLP) and instance segmentation for fine-grain computer vision. Lastly, take away best practices from Autodesk based on its experience with PyTorch on Amazon SageMaker for a range of NLP use cases. Session Kris Skrinak Alexander O'Connor Joe Spisak
AIM412-R1 - [REPEAT 1] Deep learning applications with PyTorch, featuring Freshworks With support for PyTorch in Amazon SageMaker, you have a flexible deep learning framework combined with a fully managed machine learning solution to transition seamlessly from research prototyping to production deployment. In this session, hear from the PyTorch team on the latest features and library releases. Also learn how to develop with PyTorch using Amazon SageMaker for key use cases such as using a BERT model for natural language processing (NLP) and instance segmentation for fine-grain computer vision. Lastly, hear from Freshworks about how it reduced the time to train 20,000+ models from 15 hours to 30 minutes using PyTorch and Amazon SageMaker. Session Kris Skrinak Tarkeshwar Thakur Joe Spisak
AIM413 - Deep dive on Project Jupyter Amazon SageMaker offers fully managed Jupyter notebooks that you can use in the cloud so you can explore and visualize data and develop your machine learning model. In this session, we explain why we picked Jupyter notebooks, and how and why AWS is contributing to Project Jupyter. We dive deep into our overall strategy for Jupyter and explain different use cases for Jupyter, including data science, analytics, and simulation. Session Brian Granger
AIM414 - Containerizing deep learning workflows Deep learning software stacks can be complex to build, optimize, and maintain. With different versions of frameworks, libraries, runtimes, and drivers for CPUs and GPUs, developers and data scientists spend much time ensuring that the full software stack works well together during upgrades and system changes. Join us for a discussion on how container technologies can address these challenges by providing training and inference environments that are lightweight, portable, consistent, and scalable. Chalk Talk Shashank Prasanna David Ping
AIM415-R - [REPEAT] Build fraud detection systems with Amazon SageMaker Fraud is an expensive problem that can damage customer trust. Many companies use a rule-based approach to detect fraudulent activity. But implementing and maintaining rules can be a complex process because fraud is constantly evolving, rules require that fraud patterns be known, and rules can lead to false positives or negatives. In this session, learn how machine learning (ML) can provide a more flexible approach. We dive deep on an ML solution using Amazon SageMaker, where the ML models don’t use rules. Instead, they’re trained to recognize fraud patterns, and they’re self-learning, enabling them to adapt. Chalk Talk Sergey Ermolin
Get More Results