janhuenermann/neurojs
A JavaScript deep learning and reinforcement learning library.
This JavaScript framework allows you to build and run deep learning models directly in your web browser. It's particularly focused on reinforcement learning tasks, such as training agents to perform actions in simulated environments. Developers can input network configurations and training data, receiving trained models or agent behaviors as output, making it useful for creating interactive web-based AI demonstrations.
4,378 stars. No commits in the last 6 months.
Use this if you are a web developer or researcher looking to experiment with deep learning, especially reinforcement learning, directly within a web browser environment for educational or demonstration purposes.
Not ideal if you are looking for a maintained, production-ready deep learning framework, as more general and actively supported alternatives like TensorFlow.js are recommended.
Stars
4,378
Forks
362
Language
JavaScript
License
MIT
Category
Last pushed
Oct 10, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/janhuenermann/neurojs"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
yoshoku/hnswlib-node
hnswlib-node provides Node.js bindings for Hnswlib
DanRuta/jsNet
Javascript/WebAssembly deep learning library for MLPs and convolutional neural networks
mvrahden/reinforce-js
[INACTIVE] A collection of various machine learning solver. The library is an object-oriented...
mvrahden/recurrent-js
[INACTIVE] Amazingly simple to build and train various neural networks. The library is an...
DrA1ex/mind-net.js
Fast and simple to use neural network implementation in pure TypeScript with GPU support!