# kmkolasinski/deep-learning-notes

Experiments with Deep Learning

Repository: https://github.com/kmkolasinski/deep-learning-notes
Canonical: https://ross.abutalabs.com/products/deep-learning-notes
Language: Jupyter Notebook
License Family: other
Last push: 2023-03-24T22:29:07+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": 3209, "days_push": 1258, "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 1347, forks 263 (observed 2026-08-28T04:04:27.657011+00:00)

## What it is
A collection of Jupyter Notebook experiments and seminar presentations on deep learning topics, including capsule pooling, custom optimizers, SELU regularization, and tf.data oversampling. It serves as educational material and research notes rather than a production library.

## Use cases
- learn deep learning concepts through hands-on notebook experiments
- understand how to implement a custom gradient descent optimizer
- see how SELU self-normalizing regularization works in Keras
- learn oversampling with tf.data.Dataset for imbalanced datasets
- find deep learning seminar presentations and study materials

## When to choose
- you want educational notebooks explaining deep learning techniques
- you are exploring experimental ideas like capsule pooling or max-normed optimizers
- you need examples of Keras regularizers or tf.data pipelines

## When to avoid
- you need a production-ready, maintained library with a license and stable API
- you want installable packages rather than notebooks to read and run
- you need actively updated content - the repo has not seen recent releases

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: deep-learning, machine-learning, data-science
- domain: deep-learning, machine-learning, tutorials
- platform: python
- tags: jupyter-notebooks, experiments, keras, tensorflow, seminars, educational

## Member repositories
- kmkolasinski/deep-learning-notes (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:27.657011+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 2026-08-30T04:42:37.195019+00:00, confidence not recorded.
  - readme: https://github.com/kmkolasinski/deep-learning-notes (fetched 2026-08-28T04:04:27.657011+00:00, sha d3fafff75efc)
- Data as of 2026-08-30T08:39:29.467469+00:00.