dennybritz/nn-from-scratch resource

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

2309 stars · 1087 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A Jupyter Notebook tutorial repository that implements a neural network from scratch in Python, accompanying a WildML blog post. It is educational code demonstrating the fundamentals of neural network computation without deep learning frameworks.

Use cases

• learn how neural networks work internally
• implement a neural network without a framework
• understand backpropagation with a worked example
• teach a deep learning fundamentals course
• study gradient descent on a small dataset

When to choose

• you want to understand the math behind neural networks
• you are a student or educator needing a minimal from-scratch example
• you prefer NumPy-only implementations over frameworks

When to avoid

• you need a production-ready deep learning framework
• you want GPU acceleration or modern architectures like transformers
• you need maintained, feature-rich tooling

Facets

learning-resource · maturity maintenance

machine-learning deep-learning machine-learning deep-learning tutorials education python neural-networks educational jupyter-notebook from-scratch numpy

Member repositories

For agents

markdown · JSON · MCP: product_card(name="dennybritz/nn-from-scratch")