Masterclasses
GOTO Berlin 2019

Tuesday Oct 22
09:00 –
16:00

Introduction to Machine Learning with TensorFlow.js

Duration: 1 Day Audience Level: Beginner Topics: Machine Learning/TensorFlow.js/Neural Networks

Description
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 4 different applications from scratch.

You will learn:

  • The essential mathematics.
  • How to find and use pre-trained models that are available on the internet.
  • How to build and train your own neural networks from scratch.
  • Finally, you will learn how to use the pre-trained models as a base and extend their functionality with a technique called "Transfer Learning".

Transfer Learning is one of the most exciting techniques in Machine Learning today. It's predicted to bring the next step-jump in AI power and most excitingly for u,s it doesn't require as much computational power to train so is perfect for browsers and specifically JavaScript.

By the end of this workshop, you will have the skills to be able to train a Machine Learning model with Transfer Learning in the browser using JavaScript.

Student
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.

Equipment
A fully charged laptop. (Sockets are also available on site.)

Syllabus

  • 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] Classifying handwritten numbers.
  • [Project 4] Transfer learning.

Organized by