Introduction to machine learning in JavaScript using TensorFlow.js

Sandeep Gupta (Google), Brijesh Krishnaswami (Google)

9:00am–12:30pm Tuesday, October 29, 2019

Location: Grand Ballroom A/B

Applications

Who is this presentation for?

JavaScript developers, web developers, application developers, backend developers, frontend developers, and data scientists

Level

New to TensorFlow

Description

If you’re a JavaScript developer who wants to jump into the exciting field of ML and learn how to incorporate ML into your web applications, TensorFlow.js makes it easy. Sandeep Gupta and Brijesh Krishnaswami provide a gentle, hands-on introduction to TensorFlow by helping you build your first ML applications directly in the browser. And you don’t even have to have ML experience.

Outline:

Learn the basics of convolutional neural networks and train a handwriting digit classifier in the browser
Build an image classifier and and train it on your data to play a game using your webcam
Build a simple speech command model that recognizes spoken words
Learn the basics of building your own text classifier
Learn how to use TensorFlow server-side using Node.js

Prerequisite knowledge

A working knowledge of HTML, CSS, JavaScript, and Chrome DevTools (or your preferred browser's DevTools)
Familiarity with neural networks (If you need an introduction or refresher, consider watching this video by 3blue1brown or this video on Deep Learning in Javascript by Ashi Krishnan.)

Materials or downloads needed in advance

BEFORE you arrive onsite, please make sure to have all the required installations downloaded to your computer (we ask you to not download onsite in order to help us protect the network bandwidth):
Laptop with a visual editor/IDE of your choice installed (VSCode, Sublime Edit etc).
A recent version of Node.js installed (we recommend using NVM to install).
A simple web-server to serve local files. A standard install of python (2.7 or 3.x) is sufficient for this.

What you'll learn

Learn to use ML in your web and JavaScript applications using TensorFlow

Sandeep Gupta

Google

Sandeep Gupta is a product manager at Google, where he helps develop and drive the road map for TensorFlow—Google’s open source library and framework for machine learning—for supporting machine learning applications and research. His focus is on improving TensorFlow’s usability and driving adoption in the community and enterprise. Sandeep is excited about how machine learning and AI are transforming lives in a variety of ways, and he works with the Google team and external partners to help create powerful, scalable solutions for all. Previously, Sandeep was the technology leader for advanced imaging and analytics research and development at GE Global Research with specific emphasis on medical imaging and healthcare analytics.

Brijesh Krishnaswami

Google

Brijesh Krishnaswami is a technical program manager on the TensorFlow team at Google. He has a master’s degree in computer science and two decades of experience in software development at various technology companies. You can find him on LinkedIn.