# jeffheaton/t81_558_deep_learning

T81-558: Keras - Applications of Deep Neural Networks @Washington University in St. Louis

Repository: https://github.com/jeffheaton/t81_558_deep_learning
Canonical: https://ross.abutalabs.com/products/t81_558_deep_learning
Homepage: https://sites.wustl.edu/jeffheaton/t81-558/
Language: Jupyter Notebook
License: NOASSERTION
License Family: other
Topics: neural-network, machine-learning, tensorflow, keras, deeplearning, gan, convolutional-neural-networks
Last push: 2026-04-25T00:25:09+00:00

## Health v2 (maintenance only)
Score: 58/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 79, release rhythm 8, longevity 100
- inputs: {"age_days": 3686, "days_push": 131, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5734, forks 2968 (observed 2026-08-28T04:09:28.360388+00:00)

## What it is
A university course repository (T81-558, Washington University in St. Louis) containing full Jupyter notebook materials for applying deep neural networks with TensorFlow/Keras. It covers CNNs, LSTMs, GANs, reinforcement learning, and applications in vision, NLP, and time series, and is superseded by a newer PyTorch version of the course.

## Use cases
- learn deep learning with Keras and TensorFlow
- self-study neural networks with Jupyter notebooks
- understand CNNs, LSTMs, and GANs through examples
- find a structured deep learning course with videos and workbooks
- learn reinforcement learning and NLP applications of neural networks
- get course materials for teaching applied deep learning

## When to choose
- you want a free, comprehensive, notebook-based deep learning curriculum
- you prefer learning with TensorFlow/Keras
- you want lecture videos plus hands-on workbooks
- you are a beginner with some programming background but no Python experience

## When to avoid
- you want the current PyTorch version of this course (use app_deep_learning instead)
- you need a production library or tool rather than educational material
- you need cutting-edge, frequently updated content
- you require a permissively licensed codebase you can redistribute

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: deep-learning, machine-learning
- domain: deep-learning, machine-learning, tutorials, computer-vision
- platform: python
- tags: keras, tensorflow, jupyter-notebooks, university-course, gan, cnn, reinforcement-learning, course-materials, natural-language-processing

## Member repositories
- jeffheaton/t81_558_deep_learning (main) score 58

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:28.360388+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 2026-08-29T17:53:22.971047+00:00, confidence not recorded.
  - readme: https://github.com/jeffheaton/t81_558_deep_learning (fetched 2026-08-28T04:09:28.360388+00:00, sha 4cafc17a54d4)
  - homepage: https://sites.wustl.edu/jeffheaton/t81-558/ (fetched 2026-08-29T08:48:50.838498+00:00, sha dafffaebb27b)
- Data as of 2026-08-30T08:39:29.467469+00:00.