Using Machine Learning Models in JavaScript Application
Talkat Open Source Summit Europe 2023 · on Tuesday, 2023-09-19· at 16:35· Room 5HTERRAZA (Floor 5), Abandoibarra Etorb., 4, 48011 Bilbao, Bizkaia, Spain·
summary
Shows how to load, run and retrain models with TensorFlow.js in Node and the browser, including a linear regression demo using arrays X/Y trained for 100 epochs that predicts ~3.2 for a five‑room house, and an image classifier using MobileNet to label cat and wine images. Covers model layers vs core ops, transfer learning, npm-distributed models, and browser backends (CPU, WASM, WebGL, WebGPU) with claims like Stable Diffusion dropping from ~30s to ~10s in the browser; highlights privacy, latency and offline benefits.
AI-written summary · about
chapters (11)
- 0:00ML in JavaScript apps
- 1:04Machine learning with JS
- 6:00TensorFlow.js vs Python
- 10:35Models in the browser
- 13:45ML model types
- 15:10ML workflow
- 17:19Linear regression demo
- 22:44Image classification demo
- 26:44What's new in TensorFlow.js
- 29:15Node.js ML use cases
- 30:41JS as ML gateway
related talks
32mUsing Machine Learning Models in JavaScript Application
24mTensorFlow.js + Node
15mThe future of machine learning using JavaScript
21mA Journey into the World of Machine Learning with TensorFlow.js
37mMachine Learning Principles, with JavaScript?
37mTensorFlow.js - Bringing ML and Linear Algebra to Node.js
34mA Powerful Introduction to Machine Learning with Js
37mMachine Learning Principles, with JavaScript?