(All Times IST)
Building an IoT application
Overview of services to create an end to end pipeline for IoT.
| Time | Module | Speaker | Notes |
|---|---|---|---|
| 1:00-2:00 PM | Overview of Amazon QuickSight | Durga Mishra, AWS Analytics Specialist | A QuickSight Overview and Demo |
| 2:00-4:00 PM | LAB: IoT Analytics Workshop | In this workshop, you will learn about the different components of AWS IoT Analytics. You will configure AWS IoT Core to ingest stream data from the AWS Device Simulator, build an analytics pipeline using AWS IoT Analytics, visualize the data using Amazon QuickSight, and perform machine learning using Jupyter Notebooks. | |
| BREAK | Take a break at your convenience during the lab | ||
| 4:00-5:00 PM | Overview of Amazon IoT | Gavin Adams, AWS IoT Specialist | Overview of Amazon IoT ecosystem |
| 5:00-6:00 PM | Amazon Kinesis Deep Dive | Pratik Patel, AWS Techincal Account Manager | Overview of Amazon Kinesis to provide real time ingestion services to your applications |
(All Times IST)
Amazon Sagemaker Overview of AWS AI and ML, with deeper dive into Amazon Sagemaker, capabilities to support machine learning use cases.
| Time | Module | Speaker | Notes |
|---|---|---|---|
| 1:00-1:45 PM | Overview of Machine Learning and AI on AWS | Jason Hoog, AWS Solution Architect | Overview of the AWS Artificial Intelligence and Machine Learning services to support creation of intelligent applications. |
| 1:45-2:45 PM | Create Model, Prediction and Inference | Sriram Dhandapani, AWS Technical Account Manager | Train, Tune and Deploy ML Models with Amazon SageMaker - A key aspect of training machine learning models is the ability to tune them to the highest accuracy. you will learn how to train and tune your ML models and deploy them into production. You will also learn real time and batch inference techniques to get prediction from model. |
| 2:45-3:45 PM | LAB: SageMaker Studio Notebooks & Feature Engineering | Get hands-on experience with SageMaker Console and Jupyter Notebook. Play around code to do feature engineering of sample dataset. | |
| 3:45-4:00 PM | BREAK | ||
| 4:00-5:00 PM | Understanding Built-in Algorithms | Jason Hoog, AWS Solution Architect | Built-in Machine Learning Algorithms with Amazon SageMaker and Model Evaluation - Amazon SageMaker comes built-in with a number of high-performance algorithms for different use cases. Learn the fundamentals and then dive deep into these algorithms. |
| 5:00-6:00 PM | LAB: Train, Tune and Deploy model using SageMaker Built-in Algorithm | Get hands-on experience in one of the most famous in-built ML algorithm Xgboost to build you model. Learn how you can get the best version of your machine learning model using hyperparameter tuning .Amazon SageMaker enables you to quickly and easily deploy your ML models to the most scalable infrastructure. You will learn deployment options and autoscaling for your ML models endpoint. Real time and batch inference techniques. |