A Powerful Introduction to Machine Learning with Js
summary
Shows how to run pre-trained models entirely in the browser using TensorFlow.js with WebGL GPU acceleration and manual memory disposal. Demonstrates MobileNet and COCO-SSD for image and object detection plus a client-side KNN training workflow that collects webcam frames per class for incremental training and real-time prediction, with runnable demos, code links, and discussion of practical issues like latency and RAM use.
AI-written summary · about
chapters (13)
- 0:00Machine learning with JS
- 1:08AI vs ML vs deep learning
- 3:21Neural networks and deep learning
- 5:31Classical vs ML programming
- 7:18Deep learning rise
- 9:48ML in browser
- 12:58TensorFlow.js models
- 14:45Tensors, normalization, models
- 15:27MobileNet demo
- 23:12Live image classifier
- 27:44Object classification with COCO-SSD
- 31:19Object detector details
- 33:29Conclusion
related talks
41mPractical Machine Learning for Front-End Developers
32mWe Also Can Do It! Machine Learning in Javascript!
26mMachine Learning and AI for Angular Developers
24mThe Future of Machine Learning & Javascript
36mPractical Machine Learning for Front End Developers
34mMachine learning for front-end developers
15mThe future of machine learning using JavaScript
29mSuperpowers for next gen web apps: Machine learning