Gettin’ into the (Tensor)Flow
summary
Live demos show TensorFlow running in the browser via WebGL and on Node with CPU or Nvidia GPU, including a touch-based left/right detector that reaches 100% accuracy in the demo, a repurposed speech-commands model that recognizes music chords, and a camera app that classifies charging vs not charging using a KNN classifier over MobileNet feature states. Code uses pre-trained models, exposes bias from limited training data, and pushes tiny results to Firebase for a live emoji wall.
AI-written summary · about
chapters (10)
- 0:00Start
- 1:58Smart Phones
- 3:28Machine Learning Robot
- 7:39Create a Tensor
- 7:54Operations
- 9:48Hidden Layers
- 10:52Activation Function
- 15:30Demo
- 21:07Import Tensorflow
- 21:58The Explain Function
related talks
24mTensorFlow.js + Node
01h 04mTensorFlow in your Browser
20mTensorFlow.js Bringing Machine Learning to the Web and Beyond
41mTensorFlow.js 101: ML in the Browser and Beyond
15mMachine learning for next gen web apps with TensorFlow.js
48mTensorFlow.js
34mA Powerful Introduction to Machine Learning with Js
21mA Journey into the World of Machine Learning with TensorFlow.js
