gradiatorjs

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

v0.2.2 URL: https://unpkg.com/gradiatorjs@0.2.2/dist/index.cjs

Open Browse Files

neural-network deep-learning machine-learning autodiff automatic-differentiation backpropagation gradient-descent cnn convolutional-neural-network typescript javascript browser from-scratch educational lightweight

@2bad/micrograd

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

v1.0.0 URL: https://unpkg.com/@2bad/micrograd@1.0.0/build/index.js

Open Browse Files

autodiff autograd automatic-differentiation computational-graph micrograd neural-network

scalar-autograd

Scalar-based reverse-mode automatic differentiation in TypeScript.

v0.1.8 URL: https://unpkg.com/scalar-autograd@0.1.8/dist/Value.js

Open Browse Files

autograd reverse-mode automatic-differentiation scalar typescript

micrograd

A porting of Karpathy's Micrograd to JS

v0.1.1 URL: https://unpkg.com/micrograd@0.1.1/src/index.ts

Open Browse Files

micrograd machine-learning neural-networks automatic-differentiation gradient-descent

adnn.ts

adnn provides TypeSafe Javascript-native neural networks on top of general scalar/tensor reverse-mode automatic differentiation. You can use just the AD code, or the NN layer built on top of it. This architecture makes it easy to define big, complex numer

v1.0.1 URL: https://unpkg.com/adnn.ts@1.0.1/dist/adnn.js

Open Browse Files

adnn network-network automatic-differentiation typescript isomorphic