Difference between revisions of "JavaScript"

From
Jump to: navigation, search
Line 1: Line 1:
 
[http://www.youtube.com/results?search_query=javascript+artificial+intelligence+deep+learning Youtube search...]
 
[http://www.youtube.com/results?search_query=javascript+artificial+intelligence+deep+learning Youtube search...]
  
*[[TensorFlow.js]]  
+
*[[TensorFlow.js]] for training and deploying ML models in the browser and on Node.js (was called Deeplearnjs)
*[http://playground.tensorflow.org TensorFlow Playground written in Javascript]
+
*[http://playground.tensorflow.org TensorFlow Playground written in Javascript] (TypeScript) using d3.js
 
 
  
 
A [http://news.ycombinator.com/item?id=16718285 sampling] of [http://blog.bitsrc.io/11-javascript-machine-learning-libraries-to-use-in-your-app-c49772cca46c available] Javascript Machine Learning libraries:   
 
A [http://news.ycombinator.com/item?id=16718285 sampling] of [http://blog.bitsrc.io/11-javascript-machine-learning-libraries-to-use-in-your-app-c49772cca46c available] Javascript Machine Learning libraries:   
Line 12: Line 11:
 
* [http://github.com/mljs/ml mljs]
 
* [http://github.com/mljs/ml mljs]
 
* [http://github.com/cazala/synaptic Synaptic] multilayer perceptrons, multilayer long-short term memory networks, liquid state machines and a trainer capable of training a verity of networks
 
* [http://github.com/cazala/synaptic Synaptic] multilayer perceptrons, multilayer long-short term memory networks, liquid state machines and a trainer capable of training a verity of networks
 +
* [http://mil-tokyo.github.io/webdnn/ Webdnn] this framework optimizes the DNN model to compress the model data and accelerate execution through JavaScript APIs such as WebAssembly and WebGPU 
 
* [http://wagenaartje.github.io/neataptic/ Neataptic] neuro-evolution & backpropagation for the browser
 
* [http://wagenaartje.github.io/neataptic/ Neataptic] neuro-evolution & backpropagation for the browser
 +
* [http://github.com/karpathy/convnetjs Conventjs] (not maintained)] neural networks supporting common modules, classification, regression, an experimental Reinforcement Learning module, able to train convolutional networks that process images
 +
* [http://compromise.cool/ Compromise] modest natural-language processing (NLP) interprets and pre-parses English and makes some reasonable decisions
 +
* [http://github.com/NeuroJS Neuro.js] [http://janhuenermann.com/projects/learning-to-drive Learning to Drive project] a deep learning and reinforcement learning Javascript library framework for the browser. Implementing a full stack neural-network based machine learning framework with extended reinforcement-learning support
 +
  
 
________________________________
 
________________________________

Revision as of 09:29, 5 August 2018

Youtube search...

A sampling of available Javascript Machine Learning libraries:

  • mxnet.js
  • webdnn
  • brain.js several types of networks
  • mljs
  • Synaptic multilayer perceptrons, multilayer long-short term memory networks, liquid state machines and a trainer capable of training a verity of networks
  • Webdnn this framework optimizes the DNN model to compress the model data and accelerate execution through JavaScript APIs such as WebAssembly and WebGPU
  • Neataptic neuro-evolution & backpropagation for the browser
  • Conventjs (not maintained)] neural networks supporting common modules, classification, regression, an experimental Reinforcement Learning module, able to train convolutional networks that process images
  • Compromise modest natural-language processing (NLP) interprets and pre-parses English and makes some reasonable decisions
  • Neuro.js Learning to Drive project a deep learning and reinforcement learning Javascript library framework for the browser. Implementing a full stack neural-network based machine learning framework with extended reinforcement-learning support


________________________________


Node.js

Youtube search...