Difference between revisions of "JavaScript"
(→A sampling of available Javascript Machine Learning libraries) |
|||
| Line 22: | Line 22: | ||
* [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://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 | ||
* [[ConvNetJS]] an NPM version is also available for those using Node.js, and the library is designed to make proper use of JavaScript’s asynchronicity. | * [[ConvNetJS]] an NPM version is also available for those using Node.js, and the library is designed to make proper use of JavaScript’s asynchronicity. | ||
| − | |||
* [http://github.com/mljs/ml mljs] includes supervised and unsupervised learning, artificial neural networks, regression algorithms and supporting libraries for statistics, math etc. | * [http://github.com/mljs/ml mljs] includes supervised and unsupervised learning, artificial neural networks, regression algorithms and supporting libraries for statistics, math etc. | ||
* [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 | ||
| Line 28: | Line 27: | ||
* [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://stevenmiller888.github.io/mindjs.net/ Mind] make predictions, using a matrix implementation to process training data and enabling configurable network topology. | * [http://stevenmiller888.github.io/mindjs.net/ Mind] make predictions, using a matrix implementation to process training data and enabling configurable network topology. | ||
| − | |||
* [http://deepforge.readthedocs.io/en/latest/deployment/overview.html DeeForge] a development environment for deep learning | * [http://deepforge.readthedocs.io/en/latest/deployment/overview.html DeeForge] a development environment for deep learning | ||
| + | * [http://github.com/dmlc/mxnet.js/ MXnet.js] deep learning in browser (without server); allows you to mix symbolic and imperative programming on the fly with a graph optimization layer for performance | ||
==== [http://neo4j.com/use-cases/artificial-intelligence-analytics/ Graphs Are Fundamental to Modern AI Systems | neo4j] ==== | ==== [http://neo4j.com/use-cases/artificial-intelligence-analytics/ Graphs Are Fundamental to Modern AI Systems | neo4j] ==== | ||
Revision as of 08:04, 7 April 2019
Youtube search... ...Google search
- 10 Javascript IoT Libraries To Use In Your Next Project | Jonathan Saring
- Neural networks in JavaScript - Brain.js | Robert Plummer
- Visualization
- Natural Language Processing and Machine Learning in JavaScript | David Luecke - Medium
Contents
A sampling of available Javascript Machine Learning libraries
- Libraries for NLP see Natural Language Tools & Services
- TensorFlow.js for training and deploying ML models in the browser and on Node.js (was called Deeplearnjs)
- Keras.js No longer active - capability now is in TensorFlow.js
- Deeplearnjs
- brain.js in browser and node.js ..see introduction
- 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
- TensorFire is a framework for running neural networks in the browser, accelerated by WebGL
- Conventjs (not maintained)] neural networks supporting common modules, classification, regression, an experimental Reinforcement Learning module, able to train convolutional networks that process images
- ConvNetJS an NPM version is also available for those using Node.js, and the library is designed to make proper use of JavaScript’s asynchronicity.
- mljs includes supervised and unsupervised learning, artificial neural networks, regression algorithms and supporting libraries for statistics, math etc.
- 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
- Mind make predictions, using a matrix implementation to process training data and enabling configurable network topology.
- DeeForge a development environment for deep learning
- MXnet.js deep learning in browser (without server); allows you to mix symbolic and imperative programming on the fly with a graph optimization layer for performance
Graphs Are Fundamental to Modern AI Systems | neo4j
- Why Knowledge Graphs Are Foundational to Artificial Intelligence | Jim Webber
- Creating The Most Sophisticated Recommendations Using Native Graphs | Emil Eifrem
- Neo4j Machine Learning Extensions
- Review prediction with Neo4j and TensorFlow | David Mack
- Knowledge Graphs
- D3js.org - D3.js v4 Force Directed Graph with Labels
- TensorFlow Deep Playground an interactive visualization of neural networks, written in TypeScript using d3.js and can be repurposed for different means
________________________________
Node.js
