Microjax: A Simplified Autograd Engine with Jax-like API
By
joelburget
Crispy enough to crunch, soft enough to enjoy. A good bake.
Summary
Microjax is a tiny autograd engine with a Jax-like API inspired by Micrograd and JAX, offering a functional style for machine learning. The tutorial simplifies concepts from autograd and packages them as a notebook.
Key quotes
· 3 pulledThis is inspired by Andrej Karpathy's Micrograd, a PyTorch-like library in about 150 lines of code.
Despite PyTorch's popularity, I prefer the way JAX works because it a more functional style.
My main contribution is simplifying a bit and packaging it as a notebook.
You might also wanna read
jank compiler gains custom intermediate representation to boost performance
The article discusses jank, a Clojure dialect compiler, which now has a custom intermediate representation (IR) to optimize performance and
Minicule: AI-Powered Platform for Biomedical Research Visualization and Knowledge Graph Creation
Minicule is an AI-powered research web application that connects to major scientific databases including PubMed, OpenAlex, and USPTO. The pl
Jujutsu (jj): A Git-Compatible Version Control System Focused on Simplicity and Power
Jujutsu (jj) is a Git-compatible version control system designed to be both simple and powerful. It abstracts the user interface and version
Tinybird: A Scalable Analytics Backend for Applications
Tinybird is an analytics backend infrastructure designed to handle billions of rows of data, making it easy to create real-time analytics AP
Jentic Mini: Open-Source API Execution Layer for AI Agents
Jentic Mini is a self-hosted, open-source API execution layer that solves the problem of building AI agents that need to call real APIs. It
