Introduction to Machine Learning with TensorFlow.js

Imperial Ballroom C

Audience Level: Beginner
Topics: Machine Learning/TensorFlow.js/Neural Networks

Learn how to build and train Neural Networks using the most popular machine learning framework for JavaScript, TensorFlow.js.

This is a practical workshop where you’ll learn “hands-on” by building 5 different applications from scratch using TensorFlow.js.

By the end you’ll know:
– The *essential* mathematics.
– What are Neural Networks?
– How to build and train a Neural Network to solve regression and classification tasks.
– How to find, convert, load and use pre-trained models from the internet.

If you have ever been interested in Machine Learning, if you want to get a taste for what this exciting field has to offer, if you want to be able to talk to other Machine Learning/AI specialists in a language they understand, then this workshop is for you.

The ideal student for this workshop is someone with existing experience with JavaScript. You must have experience running commands on the command line. You are experienced running NodeJS scripts. You know how to `npm install` a package.

A fully charged laptop.

Taught by Asim Hussain, co-organiser of the AI JavaScript London Meetup, co-creator of and member of the W3C WebMachineLearning Community Group Asim has been teaching JavaScript for many years and is the author of the book Angular: From Theory to Practice.

– Overview of AI + ML
– Neural Networks
– History of TensorFlow and TensorFlow.JS?
– [Project 1] Using a pre-trained model.
– [Project 2] Linear & polynomial regression.
– [Project 3] Multi-variate regression.
– [Project 4] Classifying handwritten numbers.
– [Project 5] Transfer learning