mvrahden/recurrent-js

[INACTIVE] Amazingly simple to build and train various neural networks. The library is an object-oriented neural network approach (baked with Typescript), containing stateless and stateful neural network architectures.

41
/ 100
Emerging

This library helps software developers quickly build and train various neural network architectures, primarily for educational exploration rather than production use. It takes raw data inputs, processes them through different network types like Feedforward, Recurrent, or Bayesian networks, and outputs predictions or classifications. Developers can use this to understand how neural networks are constructed and trained.

Used by 1 other package. No commits in the last 6 months. Available on npm.

Use this if you are a JavaScript/TypeScript developer who wants to learn about or experiment with implementing different neural network types and their training processes.

Not ideal if you need a robust, production-ready neural network library for real-world applications or if you require advanced recurrent neural network features with an up-to-date API.

neural-networks machine-learning-education software-development algorithm-prototyping
Stale 6m
Maintenance 0 / 25
Adoption 7 / 25
Maturity 25 / 25
Community 9 / 25

How are scores calculated?

Stars

18

Forks

2

Language

TypeScript

License

MIT

Last pushed

Jul 07, 2018

Commits (30d)

0

Reverse dependents

1

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/mvrahden/recurrent-js"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.