Oberheim SEM state-variable filter (–12 dB/oct multimode)

Web primitive layer implementations for xPU: one reference per op, one implementation per backend, and tests that hold them together.

Lightweight TypeScript neural network library with back-propagation and genetic algorithms, supporting a wide range of activation functions, all without extra build or native dependencies.

Tiny library that provides timers, envelopes, and random generators

Autoencoder

neural network in typescript

A powerful, type-safe complex numbers library for JavaScript and TypeScript. Works seamlessly in browsers and Node.js.

A set of wrapper functions to add all methods of JS' Math object to Metho:

A simple feed-forward Neural Network implementation in ES6 JavaScript

Todo:

GPU accelerated neural networks made simple for Javascript

A small neural-network implementation trained using a Genetic Algorithm (GA). Instead of backpropagation, populations of networks are evolved using fitness evaluation, crossover, selection, and mutation.

A lightweight, zero-dependency Neural Network and Matrix math library.

A TypeScript ML framework with Rust native backends (CPU, CUDA, WebGPU) — autograd, tensors, and neural network training at GPU speed.

GradiatorJS is a lightweight, from-scratch autodiff engine and a neural network library written in typescript. Featuring a powerful automatic differentiation engine using a computation graph to enable backpropagation on dynamic network architectures. You

A simple library for implementing 3 layer neural networks

Python built-in Functions and Modules in Javascript

[](https://www.npmjs.com/package/@2bad/micrograd) [](https://opensource.org/license/MIT) [![GitHub Build Status](https://img.shields.io/git

some very usefull math tools

A Modular Mathematics library