
Security News
Official Go SDK for MCP in Development, Stable Release Expected in August
The official Go SDK for the Model Context Protocol is in development, with a stable, production-ready release expected by August 2025.
micrograd-js
Advanced tools
Made for fun - to try and understand a deep learning library from scratch.
Made for fun in order to try and understand a deep learning library from scratch.
All the code is written using the "The spelled-out intro to neural networks and backpropagation: building micrograd" by Andrej Karpathy
This is written in javascript in order "to type it out" myself - in another language.
The original code is written in python which is a better language for the purpose.
But I wanted to try it out in javascript.
nodejs >= 14.17.4
I know it won't work with nodejs <= v12.22.4
nvm use v14.17.4
git clone https://github.com/diversen/micrograd-js.git
This runs the main example from the tutorial:
node test/mlp.js
This runs the OR, AND, XOR, NOT gates example:
node test/gates.js
npm install micrograd-js
import { Value } from 'micrograd-js'
import { MLP } from 'micrograd-js'
MIT © Dennis Iversen
FAQs
Made for fun - to try and understand a deep learning library from scratch.
The npm package micrograd-js receives a total of 1 weekly downloads. As such, micrograd-js popularity was classified as not popular.
We found that micrograd-js demonstrated a not healthy version release cadence and project activity because the last version was released a year ago. It has 1 open source maintainer collaborating on the project.
Did you know?
Socket for GitHub automatically highlights issues in each pull request and monitors the health of all your open source dependencies. Discover the contents of your packages and block harmful activity before you install or update your dependencies.
Security News
The official Go SDK for the Model Context Protocol is in development, with a stable, production-ready release expected by August 2025.
Security News
New research reveals that LLMs often fake understanding, passing benchmarks but failing to apply concepts or stay internally consistent.
Security News
Django has updated its security policies to reject AI-generated vulnerability reports that include fabricated or unverifiable content.