# bioinf-jku/SNNs

Tutorials and implementations for "Self-normalizing networks"

Repository: https://github.com/bioinf-jku/SNNs
Canonical: https://ross.abutalabs.com/products/snns
Language: Jupyter Notebook
License: GPL-3.0
License Family: copyleft
Last push: 2026-05-12T14:16:11+00:00

## Health v2 (maintenance only)
Score: 69/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 82, release rhythm 35, longevity 100
- inputs: {"age_days": 3373, "days_push": 113, "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 1586, forks 196 (observed 2026-08-28T04:05:07.655949+00:00)

## What it is
A collection of tutorials and reference implementations for Self-Normalizing Networks (SNNs) from Klambauer et al., demonstrating SELU activations, LeCun normal initialization, and AlphaDropout. It provides TensorFlow/Keras scripts and PyTorch Jupyter notebooks on MNIST and CIFAR10, plus supporting notebooks and calculations.

## Use cases
- learn how self-normalizing networks work
- implement SELU activation networks in Keras or PyTorch
- reproduce the SNN paper experiments on MNIST and CIFAR10
- find the correct initialization and dropout for SELU networks
- tutorial examples of AlphaDropout usage

## When to choose
- you want to learn or teach the SNN/SELU technique with runnable code
- you need reference implementations in both TensorFlow/Keras and PyTorch
- you want to reproduce results from the original SNN paper

## When to avoid
- you need a production-ready neural network library
- you want architectures beyond simple MLPs and CNNs on benchmark datasets
- you need a maintained framework rather than educational example code

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: machine-learning, deep-learning
- domain: deep-learning, machine-learning, tutorials
- platform: python, cross-platform
- tags: self-normalizing-networks, selu, keras, pytorch, jupyter-notebooks, mnist, cifar10, gpu

## Member repositories
- bioinf-jku/SNNs (main) score 69

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:07.655949+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 2026-08-30T03:55:27.883105+00:00, confidence not recorded.
  - readme: https://github.com/bioinf-jku/SNNs (fetched 2026-08-28T04:05:07.655949+00:00, sha 3df3a394709d)
- Data as of 2026-08-30T08:39:29.467469+00:00.