# rasbt/deep-learning-book

Repository for "Introduction to Artificial Neural Networks and Deep Learning: A Practical Guide with Applications in Python"

Repository: https://github.com/rasbt/deep-learning-book
Canonical: https://ross.abutalabs.com/products/deep-learning-book
Language: Jupyter Notebook
License: NOASSERTION
License Family: other
Topics: deep-learning, neural-network, machine-learning, python, tensorflow, artificial-intelligence, data-science, pytorch
Last push: 2020-10-02T04:02:21+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3545, "days_push": 2161, "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 2820, forks 739 (observed 2026-08-28T04:07:23.976604+00:00)

## What it is
Companion repository for the book 'Introduction to Artificial Neural Networks and Deep Learning: A Practical Guide with Applications in Python', containing early-access manuscript drafts, hands-on code examples, exercise solutions, and math/NumPy/PyTorch/TensorFlow appendix material. Content is primarily delivered as Jupyter notebooks implementing deep learning algorithms in PyTorch.

## Use cases
- learn deep learning and neural networks from scratch with python
- study gradient descent, backpropagation, and cost function optimization with code
- understand CNNs, RNNs, autoencoders, and GANs through runnable notebook examples
- find hands-on exercises and solutions while learning pytorch for machine learning
- brush up on linear algebra, calculus, and numpy before starting deep learning
- get a practical introduction to perceptrons and softmax regression

## When to choose
- You want theory paired with executable PyTorch notebooks rather than just reading
- You are self-studying deep learning fundamentals and want exercises with solutions
- You need refresher appendices on math notation, NumPy, and PyTorch basics

## When to avoid
- You need a production deep-learning framework or maintained codebase - this is educational material with development largely stopped around 2020
- You want TensorFlow 2.x as the primary framework - the main text centers on PyTorch and older TensorFlow material is archived
- You need a finished, published textbook - the manuscripts remain early-access drafts

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: machine-learning, deep-learning, data-science, reinforcement-learning
- domain: artificial-intelligence, machine-learning, deep-learning, data-science, tutorials
- platform: python, cross-platform
- tags: jupyter-notebooks, textbook, pytorch, tensorflow, neural-networks, education, exercise-solutions

## Member repositories
- rasbt/deep-learning-book (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:23.976604+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 2026-08-30T07:38:32.582268+00:00, confidence not recorded.
  - readme: https://github.com/rasbt/deep-learning-book (fetched 2026-08-28T04:07:23.976604+00:00, sha e8f0d158364c)
- Data as of 2026-08-30T08:39:29.467469+00:00.