# aigamedev/scikit-neuralnetwork

Deep neural networks without the learning cliff! Classifiers and regressors compatible with scikit-learn.

Repository: https://github.com/aigamedev/scikit-neuralnetwork
Canonical: https://ross.abutalabs.com/products/scikit-neuralnetwork
Language: Python
License: BSD-3-Clause
License Family: permissive
Archived: true
Last push: 2021-02-07T05:11:40+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 4174, "days_push": 2033, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1204, forks 216 (observed 2026-08-28T04:03:58.751198+00:00)

## What it is
A Python library providing deep neural network classifiers and regressors with a scikit-learn-compatible API, wrapping Lasagne and Theano. It supports MLPs, auto-encoders, convolutional layers, and common optimizers and regularization techniques.

## Use cases
- train a neural network classifier with a scikit-learn-style API
- fit a multi-layer perceptron regressor in Python
- use convolutional layers without writing Theano code
- apply dropout and L2 regularization to a deep network
- run neural networks on numpy or pandas data

## When to choose
- you want scikit-learn-compatible deep learning estimators
- you're already using Theano/Lasagne and want a friendlier interface

## When to avoid
- you need modern frameworks like PyTorch or TensorFlow
- you need recurrent networks or recent GPU features
- you need actively maintained software

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning
- domain: machine-learning, deep-learning, data-science
- platform: python
- tags: scikit-learn, neural-networks, lasagne, theano, wrapper

## Member repositories
- aigamedev/scikit-neuralnetwork (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:58.751198+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 2026-08-30T06:19:38.672881+00:00, confidence not recorded.
  - readme: https://github.com/aigamedev/scikit-neuralnetwork (fetched 2026-08-28T04:03:58.751198+00:00, sha 3b08168f038e)
  - registry_pypi: https://pypi.org/pypi/scikit-neuralnetwork/json (fetched 2026-08-29T12:27:12.913230+00:00, sha 2cd0abad9a4c)
- Data as of 2026-08-30T08:39:29.467469+00:00.