The Future of JavaScript & Machine Learning
summary
JavaScript now runs real neural nets in the browser using TensorFlow.js, the evolution of deeplearn.js, with WebGL acceleration and Node.js bindings. Demos include Teachable Machine, Style Transfer, Move Mirror (PoseNet), Sketch RNN and a webcam-controlled Pac‑Man that retrains MobileNet on the fly. Benchmarks report Python+CUDA <3 ms, Python CPU ≈60 ms, and TensorFlow.js ≈11 ms on a discrete GPU or ≈100 ms on integrated graphics, showing practical interactive performance.
AI-written summary · about
chapters (8)
- 0:00Start
- 1:14Learning & JavaScript
- 2:24What is AI, Machine Learning & Data Science?
- 4:21Artificial Neural Networks
- 13:38TensorFlow.js
- 30:17Applications of ML with JavaScript
- 31:42Getting Started
- 33:32The Future of ML & JavaScript
related talks
32mDeep Learning in JS
34mThe Browser, The Machine Learning and The Future we might not have imagined just less than a year ago
15mThe future of machine learning using JavaScript
15mMachine learning for next gen web apps with TensorFlow.js
54mDeep Learning in JS
24mThe Future of Machine Learning & Javascript
20mTensorFlow.js Bringing Machine Learning to the Web and Beyond
28mMachine Learning on the web with TensorFlow.js