Machine Learning and AI for Angular Developers
summary
Explains how to run machine learning entirely in the browser using TensorFlow.js and WebGL so inference happens client-side (avoiding server cost, latency and privacy leaks). Shows a live webcam demo using the COCO-SSD pre-trained model that correctly detects people and objects, and notes models can be retrained or built from scratch though typical training needs on the order of 40–50k images, backprop and GPUs; mentions networks with several hundred hidden layers and several thousand neurons per layer.
AI-written summary · about
chapters (9)
- 0:00Introduction to AI and ML
- 3:25How machine learning works
- 9:52Neural networks explained
- 15:14Why ML became popular now
- 17:22ML in Angular applications
- 19:11Web-based machine learning
- 21:47Demo with TensorFlow.js
- 22:57Applications of ML in Angular
- 25:09Resources and conclusion
related talks
34mA Powerful Introduction to Machine Learning with Js
34mA Powerful Introduction to Machine Learning with Js
41mPractical Machine Learning for Front-End Developers
41mTensorFlow.js 101: ML in the Browser and Beyond
41mAI in Web: TensorFlow js
23mNode.js = Machine Learning
29mSuperpowers for next gen web apps: Machine learning
24mThe Future of Machine Learning & Javascript