Offer Your Customers Real-Time Personalized Recommendations (Level 100)

Businesses of all sizes are trying to meet their users expectations of personalized recommendations in online shopping, online streaming content, and their digital media libraries of books, articles, music and podcasts. In this session we’ll share how customers have leveraged the personalization experience from Amazon.com, to offer product recommendations, similar item recommendations, and create re-ranking within each user experience. With no prior machine learning experience you can start creating A/B tests to see the impact of Amazon Personalize on increasing user engagement with your recommended products and content.

Speaker: Divyesh Sah, AWS Solutions Architect
Duration: 30mins

Overcome Document Processing and Analysis Challenges at Scale (Level 100)

Today, many financial services and healthcare organizations use documents to gather customer data via loan applications, rental agreements, patient intake forms, or medical claims forms. These documents hold valuable information the organization needs to process and understand. In this session, we will discuss how using Amazon Textract, Amazon Comprehend, and Amazon Augmented AI provide organizations with a machine learning solution, no experience required, to overcome document processing and analysis at scale.

Speaker: Mudit Mangal, AWS Solutions Architect
Duration: 30mins

AWS Security: Where We’re Going and Where We've Been (Level 100)

Here the latest security updates in the Well-Architected categories of detection, identity management, data protection, and incident response.

Speaker: Shelbee Eigenbrode, AWS Sr. AI/ML Specialist Solution Architect
Duration: 30mins

Intelligent Search to Improve Workforce Productivity (Level 200)

Amazon Kendra provides highly accurate and easy to use search powered by machine learning. This session will provide a high level overview of cognitive search, why it's important, and what it can do for your customers and employees. We will discuss on how Amazon Kendra delivers powerful natural language search capabilities to your websites and applications so your end users can more easily find the information they need.

Speaker: Ryan Peterson, AWS Solutions Architect
Duration: 30mins

Bring the Power of Machine Learning to Your Fight Against Online Fraud (Level 200)

Amazon Fraud Detector overcomes online fraud by using your data, machine learning (ML), and more than 20 years of fraud detection expertise to automatically identify potentially fraudulent online activity, allowing you to catch fraud faster. In this session, we will provide a deep dive into Amazon Fraud Detector, its use cases in your business, and how to quickly get started.

Speaker: Tim Wu, AWS Solutions Architect
Duration: 30mins

Well-Architectured Framework for Machine Learning (Level 200)

Artificial intelligence (AI) and machine learning (ML) help organizations improve outcomes with automation, predictive insights, natural language interactions, and data-driven decision making. The AWS Well-Architected Framework helps to build secure and resilient infrastructure for applications and workloads. In this whiteboarding session, learn how to design an ML application guided by the AWS Well-Architected Framework five pillars: operational excellence, security, reliability, performance efficiency, and cost optimization.

Speaker: Shelbee Eigenbrode, AWS Sr. AI/ML Specialist Solution Architect
Duration: 30mins

Prepare your Datasets at Scale using Apache Spark and SageMaker Data Wrangler (Level 300)

Pandas doesn’t scale for large datasets. Apache Spark is an open source, distributed processing engine that scales to large datasets across a large number of cluster instances. In this session, I will demonstrate several ways to use Apache Spark on AWS to analyze large datasets, perform data quality checks, transform raw data into machine learning features, and train predictive models. I will also demonstrate how SageMaker Data Wrangler uses Apache Spark to detect bias in our datasets.

Speaker: Chris Fregly, AWS Senior Advocate, AI/ML
Duration: 30mins

Orchestrate and Automate Machine Learning Workflows with SageMaker Pipelines (Level 300)

Developing a high-quality ML model involves many steps. We typically start with exploring and preparing our data. We experiment with different algorithms and parameters. We spend time training and tuning our model until the model meets our quality metrics and is ready to be deployed into production. Orchestrating and automating workflows across each step of this model development process can take months of coding. In this session, you'll see how to create, automate, and manage end-to-end ML workflows using Amazon SageMaker Pipelines. We will create a reusable NLP model pipeline to prepare data, store the features in a feature store, fine-tune a BERT model, and deploy the model into production if it passes our defined quality metrics. 

Speaker: Antje Barth, AWS Sr Developer Advocate
Duration: 30mins

Comparing Models in Production with Multi-Armed Bandits and Reinforcement Learning (Level 300)

Using the popular Hugging Face Transformers open source library for BERT, I will train and deploy multiple natural language understanding (NLU) models and compare them in live production using reinforcement learning to dynamically shift traffic to the winning model. Next, I will describe the differences between A/B and multi-armed bandit tests including exploration-exploitation, reward-maximization, and regret-minimization. Last, I will dive deep into the details of scaling a multi-armed bandit architecture on AWS using a real-time, stream-based text classifier with TensorFlow, PyTorch, and BERT on 150+ million reviews from the Amazon Customer Reviews Dataset.

Speaker: Chris Fregly, AWS Senior Advocate, AI/ML
Duration: 30mins

Reduce Training Time and Cost with SageMaker Debugger (Level 300)

Manual debugging is a common productivity drain in the machine learning lifecycle. Identifying underperforming training jobs requires constant developer attention and deep domain expertise. Just as unit tests boost traditional software development, an automated ML debugging library can save time and money. Amazon SageMaker Debugger is a ML feature that provides a set of rules that automatically identify model- and performance-related issues and stops underperforming training jobs. Debugger automatically captures relevant data during training and evaluation and presents it for online and offline inspection. In this session, we walk through how to use the real-time training metrics and set up alerts so you can reduce troubleshooting time, training costs and improve model quality. 

Speaker: Nathalie Rauschmayr, AWS Applied Scientist
Duration: 30mins

Standardize and Automate Your Feature Engineering Workflows with SageMaker Feature Store (Level 300)

As a data scientist, you certainly spend a lot of time crafting feature engineering code. Indeed, given the experimental nature of this work, even a small project can lead to multiple iterations. Thus, you’ll often run the same feature engineering code again and again, wasting time and compute resources on repeating the same operations. In large organizations, this may cause an even greater loss of productivity, as different teams often run identical jobs, or even write duplicate feature engineering code because they have no knowledge of prior work. As models are trained on engineered datasets, it’s also imperative that you apply the same transformations to data used for prediction. This often means rewriting your feature engineering code (sometimes in a different language), integrating it in your prediction workflow, and running it at prediction time. This whole process is not only time-consuming, it can also introduce inconsistencies, as even the tiniest variation in your data transforms can have a large impact on predictions. In this hands-on session, you’ll learn how to solve all these problems with Amazon SageMaker Feature Store, and how to use it with both the SageMaker Studio user interface and the SageMaker SDK. You’ll also see how it works together with SageMaker Data Wrangler to simplify your end to end data preparation workflows.

Speaker: Julien Simon, AWS Principal Advocate, ML/AI
Duration: 30mins

Scale your Large Distributed Training Jobs with Data and Model Parallelism Optimized for Amazon SageMaker (Level 300)

As State-of-the-Art (SOTA) models for NLP and CV tasks grew in size considerably over past few years, it’s no longer feasible to train these large models on single machine due to memory and time constraints. In this demo session, learn about Amazon SageMaker Distributed Training (SDT) service which allows efficiently distribute training tasks across large compute clusters. Attendees will develop intuition about two approach to distribute your training tasks (model parallelism and data parallelism) and learn how to implement both approaches using SDT for popular NLP and CV model architectures.

Speaker: Vadim Dabravolski, AWS Sr AI/ML Specialist Solution Architect
Duration: 30mins

Build your Own Defect and Anomaly Detection Models Without ML Skills  (Level 200)

How can development teams add smart capabilities to business applications without any ML skills? In this hands-on session we will focus on two specific use cases related to anomaly detection. We'll dive into the practical steps of how to identify product defects in images and how to detect outliers and issues in business metrics.

Speaker: Alex Casalboni, AWS Sr Developer Advocate
Duration: 30mins

Deploy State of the Art ML Models and Solutions in a Single Click (Level 200)

There are many challenges in getting started with machine learning (ML). Developers who are new to this field often struggle with importing a model from a popular model zoo and deploying it to an API endpoint. Additional components are also needed to launch a working ML application, including API gateways, serverless compute, object storage, ETL streams, dashboards, and authentication. Thus, the end-to-end process of building a solution can take months or longer for new ML users. In this talk, I will show you can easily and quickly bring ML applications to market. I will demonstrate how to deploy solutions using out-of-the-box ML models, and how to customize them for a specific business problem. With just a few clicks, I will show you how to launch ML solutions preconfigured with all AWS resources required for production, including a CloudFormation template and a reference architecture.

Speaker: Sebastian Stormacq, AWS Principal Developer Advocate
Duration: 30mins

Build Quality ML Models Quickly & Easily with Amazon SageMaker Autopilot (Level 300)

Building machine learning (ML) models has traditionally required a binary choice. On one hand, you could manually prepare the features, select the algorithm, and optimize the model parameters in order to have full control over the model design. However, this approach requires deep ML expertise. On the other hand, if you don’t have that expertise, you could use an automated approach (AutoML) to model generation that takes care of all of the heavy lifting, but provides very little visibility into how the model was created. While a model created with AutoML can work well, you may have less trust in it because you can’t understand what went into it, you can’t recreate it, and you can’t learn best practices which may help you in the future. In this session I am going to show you how SageMaker Autopilot eliminates this choice, allowing you to automatically build machine learning models without compromises, explore different solutions to find the best model, and then directly deploy the model to production with just one click.

Speaker: Ramu Ponugumati, AWS Sr. Technical Acct Mgr
Duration: 30mins

Automate Code Reviews, Performance Recommendations and Operational Insights (Level 200)

A better understanding of your code base helps reduce overall costs, improves non-functional behaviours like application response times and performance, and allows you to tackle issues faster and more accurately. Similarly, from the operational front, it can be difficult to identify operational issues long before they impact your customers. In this session, learn about Amazon CodeGuru, a developer tool for automating code reviews to detects issues such as Deadlocks, Data races on thread unsafe classes, Atomicity violations and Over-synchronization related concurrency bugs and automating performance reviews through application profiling to identify the lines of expensive object recreation, usage of inefficient libraries, too much logging, concurrency issues, etc that improves code performance for applications in production. This session will also cover Amazon DevOps Guru which makes it easier for developers and operators to automatically detect operational issues and recommend options for remediation or mitigation that improves the overall application availability, operational performance, reduce expensive downtime and provides Operational insights.

Speaker: Aashmeet Kalra, AWS Senior Solution Architect
Duration: 30mins

Select the Right ML Instance for your Training and Inference Job (Level 200)

AWS offers a breadth and depth of machine learning (ML) infrastructure for training and inference workloads that you can use through either a do-it-yourself approach or a fully managed approach with Amazon SageMaker. In this session, explore how to choose the proper instance for ML training and inference based on model size, complexity, throughput, framework choice, inference latency and portability requirements. Join this session to compare and contrast compute-optimized CPU-only instances, such as Amazon EC2 C4 and C5; high-performance GPU instances, such as Amazon EC2 G4, P3, and P4d; cost-effective variable-size GPU acceleration with Amazon Elastic Inference; and high performance/cost with Amazon EC2 Inf1 instances powered by custom-designed AWS Inferentia chips.

Speaker: Shashank Prasanna, AWS Senior Advocate, AI/ML
Duration: 30mins

Detect Potential Bias in your Datasets and Explain how your Models Predict using SageMaker Clarify (Level 300)

As ML models are built by training algorithms that learn statistical patterns present in datasets, several questions immediately come to mind. First, can we ever hope to explain why our ML model comes up with a particular prediction? Second, what if our dataset doesn’t faithfully describe the real-life problem we were trying to model? Could we even detect such issues? Would they introduce some sort of bias in imperceptible ways? These are not speculative questions at all, and their implications can be far-reaching. Unfortunately, even with the best of intentions, bias issues may exist in datasets and be introduced into models with business, ethical, and legal consequences. It is thus important for model builders and administrators to be aware of potential sources of bias in production systems. In addition, many companies and organizations need ML models to be explainable before they can be used in production. In fact, some regulations explicitly require model explainability for consequential decision making. In this hands-on session, you’ll learn how Amazon SageMaker Clarify can help you tackle bias and explainability issues, and how to use it with both the SageMaker Studio user interface and the SageMaker SDK. You’ll also see how it works together with SageMaker Model Monitor to track bias metrics over time on your prediction endpoints.

Speaker: Julien Simon, AWS Principal Advocate, ML/AI
Duration: 30mins

How to Accelerate Your Models to Production with SageMaker

Amazon SageMaker includes modules that can be used together or independently to build, train, and deploy your machine learning models. In this technical deep dive, we'll demonstrate SageMaker's advanced features that help you train and iterate on your machine learning models faster. You'll learn operational techniques to turn your machine learning research project into a production-ready micro-service.

Speaker: Sean Wilkinson, AWS Machine Learning Specialist Solutions Architect
Duration: 30mins

A Developer’s Guide to Choosing the Right GPUs for Deep Learning

As a deep learning developer or data scientist, you can choose from multiple GPU EC2 instances types based on your training and deployment requirements. Attend this talk to learn how you can choose the right GPU instance on AWS to meet your target performance goals. Take home guidance on maximizing resource utilization to find performance bottlenecks and reduce overall training and inference costs.

Speaker: Shashank Prasanna, AWS Senior Advocate, AI/ML
Duration: 30mins

Confessions of an AI/ML Startup Founder 

Through triumphs and missteps, founders learn invaluable lessons and build new skillsets, leading them to greater heights. You are invited to learn from some of the world's top AI/ML founders for practical lessons, advice and stories that every founder should know. Explore state of the art ML, discover how to avoid common AI/ML mistakes, and learn how to incorporate diversity and sustainability practices into your ML startup.

Speaker: Ari Kalfayan, AWS Senior Business Development Manager
Duration: 30mins

Scaling Your Startup: How to Build an Incredible Business by Leveraging Existing Tools 

Transitioning from a single engineer on a single laptop to a team of engineers can be painful. It's essential to leverage cloud services and tools to not only scale your product, but your team. In this session, learn how to: set up a data lake and implement into an ML experimental workflow, understand just enough data infrastructure and ML to be effective, and prepare an end-to-end workflow to easily share the workload.

Speaker: Rob Ferguson, AWS Principal Machine Learning Business Development Manager for Startups and Venture Capital
Duration: 30mins

Build AI-Powered Applications Without Any Machine Learning Expertise

For startups just getting their feet wet in machine learning, we’ll showcase the fastest ways to add intelligence into your products and applications—without hiring an entire ML team. Whether you’re improving your customer support workflow or automatically reviewing your code for security vulnerabilities, you’ll learn the ready-made workflows to help you improve business outcomes and raise that next round.

Speaker: Allie K. Miller, AWS Global Head of ML Business Development for Startups and Venture Capital
Duration: 30mins

Next Generation Cloud Platforms for Autonomous Development

Companies focused on Autonomous Vehicle (AV) development require extensive computing resources to accelerate the development process. Join this session to review AWS AV solutions for the toolchain including data ingest, management, labeling, simulation, and model training. You'll learn development and validation strategies to help you accelerate AV deployments, while reducing costs and time-to-market. 

Speaker: Vijitha Chekuri, AWS Principal Specialist, A.C.
Duration: 30mins

Improving ML Models with Access to More Data: Using SageMaker Data Wrangler to Integrate Multiple Data Sources Together and Power Innovation and Growth (Level: 200)

Data preparation is a critical step in the end-to-end machine learning process. Amazon SageMaker Data Wrangler is purpose-built for ML-specific data preparation workloads. In this session we discuss a new capability in Data Wrangler which allows users to quickly and easily connect to their data in Snowflake. This new capability resulted from an increased collaboration with Snowflake to help SageMaker users easily access and prepare their data from Data Wrangler and further expand the set of use cases they develop ML models for.

Speakers:
Sri Chintala, Product Manager, Snowflake
Ajai Sharma, AWS Senior Product Manager, AI

Duration: 30mins

Unlocking Value with Customer-Specific ML Models at Scale: Infusing ML into your Platform to Improve Customer Success (Level: 300)

As an ISV, building customer-specific experiences enables you to expand revenue streams, reduce churn, and increase customer satisfaction. Machine learning can power this personalized experience, but how do you build customer-specific ML models at scale if you have thousands of customers? Join us to learn how Genesys leveraged Amazon SageMaker to build its Predictive Engagement offering that trains and deploys thousands of personalized ML models completely automatically, while helping them minimize their cost.

Speakers:
Julianne Chaloux, Senior Software Engineer at Genesys
Kosti Vasilakakis, AWS Sr. Business Development Manager

Duration: 30mins

Simplifying ML Model Integrations: Leveraging the ML Models you Built with SageMaker Anywhere (Level: 200)

Organizations that manage to achieve mature forms of predictive analytics gain the competitive advantage of having foresight into their business. In this session, we will showcase how Tableau and AWS joined forces to enable that foresight by democratizing access to ML models for the BI users. We will walk you through how you can leverage the ML models built on SageMaker, right within your Tableau dashboards, and thus not only visualize the past, but also instantly predict the future. We will also discuss our integration journey, and the lessons learned when pursuing to bridge the gap between your data scientists and your business teams.

Speakers:
Madeleine Cornelli, Product Manager, Tableau
Kosti Vasilakakis, AWS Sr. Business Development Manager

Duration: 30mins

Putting ML Into The Hands Of Every User: Enabling End-Customers to Build and use ML Models with SageMaker Autopilot Right Within your own Platform (Level: 100)

With rich data available from a variety of sources, enterprises and business analysts are increasingly turning to data platforms such as Domo to integrate and analyze data from disparate sources. To gain insights from this data, analysts want the ability to create predictive models based state of the art machine learning algorithms, right where their data is. Domo AutoML, powered by Amazon SageMaker Autopilot, makes it easy to quickly create, use, and make predictions with highly accurate ML models from within Domo. Join us to learn more about how SageMaker Autopilot automatically builds, trains, and tunes the best machine learning models based on data managed by Domo, while allowing users to maintain full control and visibility, without leaving the Domo platform.

Speakers:
Sean Thompson, IT Director, Freddy’s
Tushar Saxena, Principal Product Manager, AWS
Ben Ainscough, Ph.D., Head of AI and Data Science Product, Domo

Duration: 30mins

Talkdesk shares how to add intelligence to your existing contact center with AWS Contact Center Intelligence (CCI) (Level: 200)

Learn how your organization can leverage AWS Contact Center Intelligence (CCI) solutions to improve customer experience and reduce cost with AI. We will explore how AWS CCI solutions can be built easily through an expanding network of partners to provide self-service interactions, live and post-call analytics and agent assist on existing contact center systems. AWS Partner, Talkdesk will share how they improve customer experience and tackle challenging business problems such as improving agent effectiveness, and automating quality management in enterprise contact centers.

Speakers:
Ben Rigby, VP AI, Talkdesk
Paul Lasserre, Global Solutions Lead AI/ML, AWS

Duration: 30mins

Use AWS ML Services to Analyze your Videos to Create New Insights, Automate Work, and Increase Content Value with AWS Media Intelligence (Level: 200)

In this session, dive into the most common problems facing organizations who produce, process, or archive large amounts of video and audio, and how they can better review, search, and analyze content at scale with AWS image and speech AI services. AWS and its technology partner Synchronized will share their experience helping customers from enhancing the viewer experience by streamlining operational and compliance media tasks, to more effectively monetizing content and optimizing content archives. In particular, learn how Synchronized accelerated innovation on behalf of leading TV channels using Amazon Rekognition & Rekognition Custom Labels, and Amazon Transcribe to analyze Video-on-demand (VoD) content and automating the creation of Smart thumbnails.

Speakers:
Paul Lasserre, Global Solutions Lead AI/ML, AWS 
Guillaume Doret, CEO, Synchronized TV

Duration: 30mins

Get rolling with machine learning on AWS DeepRacer (Level 200)
Developers, start your engines! This session provides developers of all skill levels an opportunity to get hands-on experience with AWS DeepRacer and hear about exciting announcements and enhancements coming to the league in 2021. Learn about the basics of machine learning and reinforcement learning (a machine learning technique ideal for autonomous driving). In this session, you can build a reinforcement learning model and submit it to the AWS DeepRacer League for a chance to win prizes and glory.

Speaker: Janos Schwellach, Specialist SA Developer, AWS
Duration: 30mins

Shift your ML model into overdrive with AWS DeepRacer analysis tools (Level 300)
Make your way from the middle of the pack to the top of the AWS DeepRacer podium. Once you have built your first reinforcement learning model, extend your machine learning skills in this session by exploring how human analysis of reinforcement learning through logs improves your performance through trend identification and optimization to better prepare for the races. 

Speaker: Donnie Prakoso, Senior Developer Advocate, AWS
Duration: 30mins

Build, train, and debug machine learning models (Level 200)
In this lab, we show the different aspects of the machine learning (ML) workflow for building, training, and deploying a model using all the capabilities of Amazon SageMaker. We also discuss how Amazon SageMaker removes the heavy lifting from each step of the ML workflow. Come learn how to build, train, debug, monitor, and deploy your ML models.

AWS DeepRacer (Level 200)
Get ready to race by building your own AWS DeepRacer reinforcement learning (RL) model. AWS DeepRacer is an integrated learning system for users of all levels that allows you to explore RL and experiment with building autonomous driving applications. In this lab, you get hands-on with creating, training, and tuning your RL model.

Reinforcement learning (Level 200)
In this lab, learn how to build reinforcement learning (RL) models using Amazon SageMaker RL, which includes prebuilt RL libraries and algorithms that help you achieve faster turnaround times and improve the results of your RL experiments.

Customer churn prediction (Level 200)
In this lab, learn how identifying unhappy customers early provides you with the opportunity to incentivize them to stay and helps decrease customer churn. In this lab, we explain how to use machine learning (ML) to predict customer churn. We also discuss how to incorporate the costs associated with prediction mistakes to determine the financial outcome of using ML.

Virtual contact center (Level 200)
This lab explains how to build a contact center using Amazon Connect and Amazon Lex. Learn how to match intent based on your input and provide greater flexibility for customers who interact with contact centers.

Movie batch recommendations (Level 200)
In this lab, we walk you through how to train and create batch recommendations using Amazon Personalize. Learn how you can perform tasks such as generating recommendations for a large number of users that will be used later for batch-oriented workflows like sending emails or notifications.

Sentiment analysis web application (Level 200)
In this lab, we demonstrate how to add artificial intelligence (AI) and machine learning (ML) cloud service features to your web application with React and the AWS Amplify Framework.

Worker safety system using customized Image and video Analysis (Level 300)
Learn how to use AWS DeepLens and Amazon Rekognition to build an application that helps identify if a person at a construction site is wearing the right safety gear, in this case, a hard hat. In this session, we show how you can create and deploy an object detection project to AWS DeepLens, modify the AWS DeepLens object detection inference Lambda function to detect persons and upload the frame to Amazon S3, create a Lambda function to identify those who are not wearing safety hats and analyze the results using AWS IoT , Amazon CloudWatch and a web dashboard.

Speaker: Imran Kashif, Principal Solutions Architect - Amazon AI, AWS

Multilingual omnichannel contact center (Level 300)
This project recognizes the contact center industry’s critical language barrier issue between agents and customers participating in a live chat conversation. It would perform real-time translation of the chat conversation between the agent and the customer and provide a chat-based output to both sides according to their desired languages (the team is also performing research to try this solution for voice-based conversations). The project leverages Amazon Connect to provide a seamless contact center experience, as well as Amazon Translate, Amazon Polly, and Amazon Transcribe.

Speakers:
Jackysh Bangera,  Solutions Architect, AWS
Gaurav Sahi, Principal Solutions Architect, AWS

Automated corrosion detection using machine learning (Level 300)
Visual inspection of industrial environments is a common requirement across heavy industries, and as a result, experts often have to perform manual inspections in adverse environments that put them at risk. Many of these industries deal with huge metal surfaces that are subject to corrosion, which poses a serious risk and huge financial impact. This demonstration showcases a machine learning approach to corrosion detection that helps visualize corroded areas. Learn how AWS Step Functions is used to create Amazon SageMaker machine learning models and deploy them for inference within a web application built with AWS Amplify and Amazon CloudFront.

Speakers:
Aravind Kodandaramaiah, Global Accounts Solutions Architect - Prototyping, AWS
Mehdi Far, Senior Solutions Architect - AI/ML, AWS

Garbage underwater detection (Level 300)
With an estimated 8 million metric tons of trash deposited into oceans each year, there are now close to 500 dead zones, where most marine life cannot survive, globally covering more than 245,000 square kilometers, equivalent to the area of the UK. Clearing this trash is a massive job requiring first knowing exactly where the trash is located. This demo shows how to use machine learning to detect trash underwater, mapping it to its location. We use services like Amazon SageMaker, Amazon Elasticsearch Service, and AWS IoT to run this model at the edge with TensorFlow and an NVIDIA Jetson AGX Xavier Developer Kit.

Speakers:
Kapil Pendse, Solutions Architect, AWS
Janos Schwellach, Solutions Architect, AWS

Sign and Speak (Level 300)
This demo showcases how the Sign & Speak program uses machine learning (ML) to build a tool that facilitates communication between users of sign language and users of spoken language. By combining artificial intelligence (AI) models trained to transcribe speech and interpret sign language with a camera and a microphone, the tool enables two-way conversation in situations where communication was previously challenging.

Speaker: Eshaan Anand, Senior Partner Solutions Architect, AWS