# iamtrask/Grokking-Deep-Learning

this repository accompanies the book "Grokking Deep Learning"

Repository: https://github.com/iamtrask/Grokking-Deep-Learning
Canonical: https://ross.abutalabs.com/products/grokking-deep-learning
Language: Jupyter Notebook
License Family: other
Last push: 2024-06-01T15:33:42+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3674, "days_push": 823, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 7722, forks 1624 (observed 2026-08-28T04:10:02.587115+00:00)

## What it is
A collection of Jupyter Notebook chapters accompanying the book 'Grokking Deep Learning' by Andrew Trask. It teaches deep learning fundamentals from scratch, covering forward propagation, gradient descent, backpropagation, CNNs, RNNs, LSTMs, and automatic differentiation.

## Use cases
- learn deep learning from scratch
- understand how backpropagation works
- build a neural network without frameworks
- study gradient descent with worked examples
- learn about LSTMs and RNNs
- understand automatic differentiation by building a mini framework

## When to choose
- you want to learn deep learning concepts from first principles
- you prefer code-driven tutorials in Jupyter notebooks
- you want to understand internals before using frameworks like PyTorch

## When to avoid
- you need a production deep learning library
- you want state-of-the-art model implementations
- you need a maintained, licensed codebase for reuse

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: deep-learning, machine-learning
- domain: deep-learning, machine-learning, tutorials
- platform: python, cross-platform
- tags: jupyter-notebooks, book-companion, neural-networks, gradient-descent, backpropagation, rnn, lstm, cnn, word-embeddings, education

## Member repositories
- iamtrask/Grokking-Deep-Learning (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:02.587115+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:35:15.790028+00:00, confidence not recorded.
  - readme: https://github.com/iamtrask/Grokking-Deep-Learning (fetched 2026-08-28T04:10:02.587115+00:00, sha fa28c01b8728)
- Data as of 2026-08-30T08:39:29.467469+00:00.