TensorFlow for JavaScript - TensorFlow at O’Reilly AI Conference, San Francisco '18
TensorFlow via YouTube
Overview
Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Explore the capabilities of TensorFlow.js, the JavaScript version of TensorFlow for browser and Node.js environments, in this 33-minute conference talk from the O'Reilly AI Conference in San Francisco. Learn about the complete machine learning workflow, including training, client-side deployment, and transfer learning through demonstrations and practical examples. Discover how to write simple models, use the Machine Learning Playground, and implement features like the Emoji Scavenger Hunt. Gain insights into performance optimization, server-side integration, and future developments in TensorFlow.js. Access additional resources, including the TensorFlow.js framework and GitHub repository, to further enhance your understanding of this powerful tool for JavaScript-based machine learning.
Syllabus
Intro
Machine Learning Playground
TensorFlow GS
Writing a simple model
Emoji Scavenger Hunt
Behind the Scenes
Save Models
PoesNet
Performance
NoGS
Code snippet
Serverside
Demo
Whats next
Highlevel bets
Cloud integrations
Wrapping up
Resources
Taught by
TensorFlow