Difference between revisions of "JavaScript"
| Line 17: | Line 17: | ||
** [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 | ** [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 | ||
** [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. | ||
** [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://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://github.com/BrainJS/brain.js brain.js] several types of networks | ** [http://github.com/BrainJS/brain.js brain.js] several types of networks | ||
Revision as of 19:36, 22 February 2019
Youtube search... ...Google search
- TensorFlow.js
- 10 Javascript IoT Libraries To Use In Your Next Project | Jonathan Saring
- Neural networks in JavaScript - Brain.js | Robert Plummer
- Visualization
- A sampling of available Javascript Machine Learning libraries:
- TensorFlow.js for training and deploying ML models in the browser and on Node.js (was called Deeplearnjs)
- Keras.js runs Keras models in the browser, with GPU support using WebGL. since Keras uses a number of frameworks as backends, the models can be trained in TensorFlow, CNTK, and other frameworks as well.
- 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
- 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.
- 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
- brain.js several types of networks
- 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
- Compromise modest natural-language processing (NLP) interprets and pre-parses English and makes some reasonable decisions
- Mind make predictions, using a matrix implementation to process training data and enabling configurable network topology.
- Natural provides tokenizing, stemming (reducing a word to a not-necessarily morphological root), classification, phonetics, tf-idf, WordNet, string similarity, and more.
- DeeForge a development environment for deep learning
- Graphs Are Fundamental to Modern AI Systems | neo4j
________________________________
Node.js
