liquidcarrot/carrot

🥕 Evolutionary Neural Networks in JavaScript

43
/ 100
Emerging

This is a JavaScript library for building neural networks using neuro-evolution. You provide the problem, and Carrot automatically designs and optimizes the neural network architecture itself, rather than you having to manually configure layers and connections. It takes in raw data for a problem you want to solve and outputs a trained, optimized neural network. This is for machine learning practitioners, researchers, and developers who need to quickly prototype or explore neural network solutions for complex problems without extensive manual design.

294 stars. No commits in the last 6 months.

Use this if you have a problem you don't know how to solve with a traditional neural network or want to discover an ideal network structure without manual design.

Not ideal if you need fine-grained control over every aspect of your neural network's architecture or are working with extremely large, high-performance deep learning models.

AI-experimentation neural-network-design evolutionary-computation unsupervised-learning algorithm-discovery
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

294

Forks

35

Language

JavaScript

License

MIT

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.