Neural Networks: Zero to Hero
Karpathy's course building neural networks from scratch, step by step.
Course
A tiny scalar-valued autograd engine with a PyTorch-like API.
Built with love by Shushant Lakhyani. Building bestproductivityresources.com
Screenshot or bookmark this page so you find it later, then share it with your network.
micrograd is Andrej Karpathy's tiny autograd engine and neural net library — a few hundred lines that implement backpropagation over scalar values with a PyTorch-like API, built for teaching how neural networks really work.
Anyone who wants to understand neural nets from first principles.
Teams looking for a production training framework.
Side-by-side comparisons and lists that include micrograd.
Similar resources to micrograd, picked from the directory.
Karpathy's course building neural networks from scratch, step by step.
Bare bones NumPy implementations of machine learning models and algorithms.
Python examples of popular ML algorithms with interactive Jupyter demos.
OpenAI's educational resource for learning deep reinforcement learning.
A straightforward method for training your LLM, from downloading data to generating text.
The simplest, fastest repository for training and finetuning medium-sized GPTs.
Free resources that cover similar ground.
Evidence-first AI workflow for economic and financial research: from topic to verifiable LaTeX draft.
Interactive deep learning book with code, math and discussions.
Microsoft's free 18-lesson course to start building AI agents.
60+ deep learning paper implementations with side-by-side notes.
Harvard's introduction to AI with Python.
Practical deep learning courses for coders.
Made micrograd? Add this free badge to your website or README. It links to this page.
<a href="https://bestproductivityresources.com/resources/micrograd" target="_blank" rel="noopener"><img src="https://bestproductivityresources.com/badges/featured-light.svg" alt="Featured on Best Productivity Resources" width="250" height="54" /></a>Open stats
This site's analytics are open for everyone to see.