AI in JavaScript

---

TensorFlow

• TensorFlow
• tensorflow.js (and github) (formerly deeplearn.js)
• MobileNet (Convolutional Neural Networks for lightweight machine vision) using tensorflow.js
• MobileNet is used in ML5.

---

ML5

• Inspired by P5. Built on tensorflow.js. Includes tensorflow utilities.

• learn.ml5js.org (docs)
  • Reference

• github
• npmjs

• releases
• ml5.min.js (v0.6.1)
• ml5.min.js.map (v0.6.1)

• ML5 examples on P5 web editor

Remote load of AI model

• ML5 can get a pre-trained AI model through a remote call.
• Example in the ML5 World Recognise any image.
• See code:

   classifier = ml5.imageClassifier ( 'MobileNet' .. 

• imageClassifier
  • The argument is one of pre-defined models ("The ml5 library accesses this model from the cloud") or else URL of some model.json
  • Model and Data Provenance

• Run the above and you see a call to get:

  https://storage.googleapis.com/.../imagenet/mobilenet.../model.json

  using CORS:

   access-control-allow-origin: * 

• Look at what is downloaded (Chrome - Network - Reload) and you should find the actual neural network is downloaded (over 10 M) and runs locally.

---

ConvNetJS

• Andrej Karpathy
  • site
  • ConvNetJS (Convolutional Neural Networks library) (see github)
  • ConvNetJs2
  • REINFORCEjs

---

Other

• Awesome Machine Learning list of libraries by language
  • JavaScript

• Other:
  • WebCNN (see demo)
  • synaptic.js
  • Keras.js
  • Limdu