# MichalDanielDobrzanski/DeepLearningPython

neuralnetworksanddeeplearning.com integrated scripts for Python 3.5.2 and Theano with CUDA support

Repository: https://github.com/MichalDanielDobrzanski/DeepLearningPython
Canonical: https://ross.abutalabs.com/products/deeplearningpython
Language: Python
License: MIT
License Family: permissive
Last push: 2023-11-27T13:07:11+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": 3687, "days_push": 1010, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2830, forks 1274 (observed 2026-08-28T04:07:24.332377+00:00)

## What it is
Python 3.5.2 port of the companion scripts for the book 'Neural Networks and Deep Learning' (neuralnetworksanddeeplearning.com), including network.py, network2.py, and network3.py with Theano and CUDA support. It serves as runnable educational code for training and evaluating the neural networks described in the book's chapters.

## Use cases
- learn how neural networks are implemented from scratch
- run the code examples from the neural networks and deep learning book
- train a simple MNIST classifier in Python
- study backpropagation and gradient descent implementations
- experiment with Theano-based convolutional networks with CUDA

## When to choose
- you are reading the book and want working Python 3 code for its examples
- you want minimal, readable educational neural network implementations
- you want to see how Theano-era deep learning code was structured

## When to avoid
- you need a modern deep learning framework like PyTorch or TensorFlow
- you want production-ready or actively maintained training code
- you cannot run Python 3.5-era dependencies such as Theano

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: deep-learning, machine-learning, gpu-computing
- domain: deep-learning, machine-learning, education, tutorials
- platform: python, cross-platform
- tags: neural-networks, theano, book-companion-code, cuda, python3, gpu

## Member repositories
- MichalDanielDobrzanski/DeepLearningPython (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:24.332377+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 2026-08-30T07:38:10.024072+00:00, confidence not recorded.
  - readme: https://github.com/MichalDanielDobrzanski/DeepLearningPython (fetched 2026-08-28T04:07:24.332377+00:00, sha 79bb40237708)
- Data as of 2026-08-30T08:39:29.467469+00:00.