Machine Learning Workshops
No 1 Learn
Workshops
Below is a collection of self-paced workshops, blog posts, and example code built by AWS employees. The workshops are grouped by services below:
Sagemaker | Deep Lens | Mechanical Turk | Deep Learning AMI
No 2 Amazon Rekognition
Social Networks with Rekognition
This is a Jupyter notebook that highlights the use of AWS Rekognition's facial identification functionality. It will identify celebrity faces (http://docs.aws.amazon.com/rekognition/latest/dg/celebrity-recognition.html) and use the Movie Graph Database (https://neo4j.com/developer/movie-database/#_download) hosted in a Neo4j database instance to render a graphical representation of the relationship between two celebrities (ala Six Degrees of Kevin Bacon).
A collection of 3 lambda functions that are invoked by Amazon S3, Amazon API Gateway, and directly (RESTful calls) to analyze uploaded images in S3 with Amazon Rekognition and save picture metadata to ElasticSearch
Build A Rekognition Powered Twitter Bot
This workshop will allow you to build a twitter bot that modifies images it receives
In this workshop, we will build a solution that automatically launches and configures Amazon Rekognition, Amazon Kinesis Firehose, Amazon Simple Storage Service(S3), AWS Lambda, Amazon DynamoDB, Amazon Simple Notification Service (SNS), & Amazon Elastic Cloud Compute (EC2) to collect, store, process, and analyze data to search for missing persons on social media data streams.
Amazon Rekognition Policing User Content
A Stepfunctions driven workflow to use Amazon Rekognition to scan incoming images through a set of business rules and police apply policing, using AWS services like Amazon Rekognition, AWS Step Functions, Amazon DynamoDB and AWS Lambda.
No 3 Amazon Polly
Convert RSS Content to Podcasts
This app allows you to easily convert any publicly available RSS content into audio Podcasts, so you can listen to your favorite blogs on mobile devices instead of reading them.
Build A Text-to-Speech Application
In this blog post, we create a basic, serverless application that uses Amazon Polly to convert text to speech. The application has a simple user interface that accepts text in many different languages and then converts it to audio files which you can play from a web browser. We’ll use blog posts, but you can use any type of text. For example, you can use the application to read recipes while you are preparing a meal, or news articles or books while you’re driving or riding a bike.
Receive Phone Call Alerts for AWS Account Security Events With Amazon Polly
Security of your AWS account is paramount. Staying up to date with any security-related events in your AWS account is important. There are various ways to get alerts- via email or SMS, however in this blog post I’m going to show you how to get a voice alert on your phone using Amazon AI services like Amazon Polly and any cloud-based communications platform like Twilio.
No 3 Amazon Lex
An example web application using the Lex JavaScript SDK to send and receive audio from the Lex PostContent API. Demonstrates how to capture an audio device, record audio, and convert the audio into a format that Lex will recognize, and play the response. All from a web browser.
This is a sample Amazon Lex web interface. It provides a chatbot UI component that can be integrated in your website. The interface allows to interact with a Lex bot directly from a browser using text or voice.
Build a Customer Service Chatbot with Amazon Lex
In this workshop, you will build a customer service chatbot for a fictitious telco company. They want to make it really easy for their customers to add an international plan to their existing phone account when their customers travel abroad for business and vacation.
In this workshop, you will build a CoffeeBot. CoffeeBot is a transactional chat bot that can help one order a mocha (relies on AWS Mobile Hub and Android).
No 6 Amazon Translate
Amazon ML Services for Video Transcription & Translation
Integrate Transcribe, Translate, and Comprehend to create captioning for videos in multiple languages.
In this post, you will create an HTML page with CSS and JavaScript. You will use a JavaScript library to connect to a Twitch channel and start receiving messages. As those real-time messages come in, you will use the AWS SDK to call Amazon Translate and get those messages translated and displayed in the UI. If you choose to use the user-enabled voice option, you’ll use AWS SDK to call Amazon Polly and get synthesized speech for those messages and play them back to the users.
Build a Social Media Dashboard using Machine Learning and BI services
In this blog post we’ll show you how you can use Amazon Translate, Amazon Comprehend, Amazon Kinesis, Amazon Athena, and Amazon QuickSight to build a natural-language-processing (NLP)-powered social media dashboard for tweets.
No 4 Amazon Transcribe
Amazon ML Services for Video Transcription & Translation
Integrate Transcribe, Translate, and Comprehend to create captioning for videos in multiple languages.
No 5 Amazon Comprehend
Amazon ML Services for Video Transcription & Translation
Integrate Transcribe, Translate, and Comprehend to create captioning for videos in multiple languages.
Detect Sentiment from customer reviews using Amazon Comprehend
In this blog post, we will show you how to leverage Amazon Comprehend as part of a serverless event driven architecture, built with AWS services, to detect customer sentiment.
Build a Social Media Dashboard using Machine Learning and BI services
In this blog post we’ll show you how you can use Amazon Translate, Amazon Comprehend, Amazon Kinesis, Amazon Athena, and Amazon QuickSight to build a natural-language-processing (NLP)-powered social media dashboard for tweets.
No 7 AWS SageMaker
Integrate Transcribe, Translate, and Comprehend to create captioning for videos in multiple languages.
This repository contains example notebooks that show how to apply machine learning and deep learning in AWS SageMaker.
U-Net and E-Net Segmentation Using AWS SageMaker
A tutorial on how to build, train, and deploy advanced CNN architectures U-Net and ENet for per-pixel binary segmentation on SageMaker.
Creates a CloudFormation template that uses AWS StepFunctions to automate the building and training of Sagemaker custom models based on S3 and GitHub events.
AWS SageMaker Seq2Seq Word Pronounciation
Sequence to Sequence modeling has seen great performance in building models where the input is a sequence of tokens (words for example) and output is also a sequence of tokens. This notebook provides an end-to-end example of training and hosting the English word pronunciation model using the Amazon SageMaker built-in Seq2Seq.
AWS SageMaker for Computer Vision
This repository contains Jupyter Notebook tutorials for computer vision use-cases.
No 8 AWS DeepLens
We will provide a hands-on learning experience by build an end-to-end systems for face detection, recognition and verification. The workshop is designed for developers that are curious about these new technologies with no ML background assumed.
AWS SageMaker for Computer Vision
This repository contains Jupyter Notebook tutorials for computer vision use-cases.
No 9 Amazon Mechanical Turk
Getting Started with Amazon Mechanical Turk
Instructions for getting started with MechTurk and the APIs available for MTurk requests.
No 10 Deep Learning AMI
This is a notebook tutorial for TensorFlow (mainly thorugh Keras) on MNIST data. You will go through building a simple fully connected (dense - DNN) network, then improve it using convolution (CNN), and then you will explore RNN (LSTM) for the same problem.
This repo contains an incremental sequence of notebooks designed to teach deep learning, MXNet, and the gluon interface. Our goal is to leverage the strengths of Jupyter notebooks to present prose, graphics, equations, and code together in one place. If we're successful, the result will be a resource that could be simultaneously a book, course material, a prop for live tutorials, and a resource for plagiarising (with our blessing) useful code.