liquidcarrot/carrot
🥕 Evolutionary Neural Networks in JavaScript
Supports population-based neuroevolution to automatically design network architectures from scratch, with mutable neurons and layers that evolve during training. Provides both high-level prebuilt architectures (Perceptron, LSTM, GRU, NARX) and low-level neuron-level APIs for custom algorithms, plus D3.js-based SVG visualization of evolved networks. Runs in Node.js and browsers via npm or CDN, with multi-threading support and GPU acceleration planned.
294 stars. No commits in the last 6 months.
Stars
294
Forks
35
Language
JavaScript
License
MIT
Category
Last pushed
Jan 07, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/liquidcarrot/carrot"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
wagenaartje/neataptic
:rocket: Blazing fast neuro-evolution & backpropagation for the browser and Node.js
uber-research/deep-neuroevolution
Deep Neuroevolution
flxsosa/DeepHyperNEAT
A public python implementation of the DeepHyperNEAT system for evolving neural networks....
alenaksu/neatjs
NEAT (Neuro Evolution of Augmenting Topologies) implementation in JavaScript
janhohenheim/Hippocrates
No longer maintained, actually usable implementation of NEAT