building intelligent solutions with aws iot

Post on 23-Jan-2018

345 Views

Category:

Documents

1 Downloads

Preview:

Click to see full reader

TRANSCRIPT

© 2016, Amazon Web Services, Inc. or its Affiliates. All rights reserved.

Neeraj Kumar

26 September 2017

Building Predictive Applications with AWS IoT &Amazon Machine Learning

Workshop

Agenda

15 mins

10 mins

20mins

20 mins

20 mins

Workshop Setup

Lab 1 – Setup Machine Learning Model

Lab 3 – Create Lambda Function

Lab 2 – Setup IoT ‘Thing’ and Rule Engine

Lab 4 - Setup and Activate device code (simulated wind turbine)

Introduction to AWS IoT & Amazon Machine Learning

20mins

Introduction

AWS IoTFully managed cloud platform that lets connected devices easily and securely interact with cloud applications and other devices

Devices Network Security Data Collection Smarts

1

Connect Billions of Devices

Lightweight Communication Protocol

X509 Certificates DynamoDB, Kinesis, and S3

Trigger Lambda Functions

Amazon Machine Learn ingCreate ML models without having to learn

complex algorithms and technology

Amazon Machine learning

Easy to use, managed machine learning service built for developers

Robust, powerful machine learning technology based on Amazon’s internal systems

Create models using your data already stored in the AWS cloud

Deploy models to production in seconds

Easy to use and developer-friendly

Use the intuitive, powerful service console to build and explore your initial models

• Data retrieval • Model training, quality evaluation, fine-tuning• Deployment and management

Automate model lifecycle with fully featured APIs and SDKs

• Java, Python, .NET, JavaScript, Ruby, Javascript

Easily create smart iOS and Android applications with AWS Mobile SDK

Build model Validate &optimize

Make predictions

1 2 3

Development process

Model Evaluation and Optimization

Batch predictionsAsynchronous predictions with trained model

Real time predictionsSynchronous, low latency, high throughputMount API end-point with a single click

Making predictions

Three supported types of predictions

Binary classificationPredict the answer to a Yes/No question

Multiclass classificationPredict the correct category from a list

RegressionPredict the value of a numeric variable

Training Parameters

Model Size

Regularization

Data Shuffling

# of Passes

High Level Design- This is what we are going to build today!

AWS Lambda

Device Gateway

Amazon Machine Learning

wind-turbine/telemetry

IoTrule

Device Shadow

AWS IoT

Wind Farm

Labs

Lab 1 – Setup Machine Learning Model

Lab 2 – Setup IoT ‘Thing’ and Rule Engine

Lab 3 – Create Lambda Function

Lab 4 - Setup and Activate device code (simulated wind farm)

We will go over these labs:

Thank you!

top related