Adventures in Javascript Machine Learning
summary
Claims that Google had over 4,000 TensorFlow models in production by 2017 and that ML can run on the client underpin concrete demos: a browser webcam sentiment demo that runs inference locally and sends only labels, a rock‑paper‑scissors classifier trained in‑browser to ~97% accuracy after training, an open‑source NSFW filter, a learning tic‑tac‑toe, and small apps using TensorFlow.js, BrainJS, React Native with GPU via WebGL; all code is published and a free 5‑day course is offered.
AI-written summary · about
chapters (11)
- 0:00Introduction and setup
- 1:03Why AI and JavaScript
- 5:39Neural networks and data
- 8:06Live facial expression demo
- 13:04Machine learning basics explained
- 20:33Real-world AI applications
- 23:48JavaScript in edge AI
- 30:35Code demo rock paper scissors
- 41:11Training and testing the model
- 44:19Resources and next steps
- 47:09Q&A session
related talks
39mMachine Learning Magic for Your JavaScript Application
24mThe Future of Machine Learning & Javascript
46mArtificial Intelligence with JavaScript
15mThe future of machine learning using JavaScript
28mMachine Learning on the web with TensorFlow.js
15mMachine learning for next gen web apps with TensorFlow.js
21mA Journey into the World of Machine Learning with TensorFlow.js
34mA Powerful Introduction to Machine Learning with Js