# rasmusbergpalm/DeepLearnToolbox

Matlab/Octave toolbox for deep learning. Includes Deep Belief Nets, Stacked Autoencoders, Convolutional Neural Nets, Convolutional Autoencoders and vanilla Neural Nets. Each method has examples to get you started.

Repository: https://github.com/rasmusbergpalm/DeepLearnToolbox
Canonical: https://ross.abutalabs.com/products/deeplearntoolbox
Language: MATLAB
License: BSD-2-Clause
License Family: permissive
Last push: 2018-10-13T18:08:01+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": 5424, "days_push": 2881, "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 3867, forks 2254 (observed 2026-08-28T04:08:27.685401+00:00)

## What it is
A Matlab/Octave toolbox implementing classic deep learning models including Deep Belief Nets, Stacked Autoencoders, Convolutional Neural Nets, Convolutional Autoencoders, and vanilla feedforward neural networks. It is explicitly deprecated and no longer maintained, with the author recommending modern frameworks like TensorFlow instead.

## Use cases
- train a deep belief network in matlab
- implement a convolutional neural network in octave
- learn how stacked autoencoders work with example code
- visualize RBM weights on MNIST
- study classic deep learning algorithm implementations
- initialize a neural network from DBN pretraining

## When to choose
- you must work in Matlab/Octave and need simple reference implementations of DBNs, autoencoders, or CNNs
- you are studying or teaching how classic deep learning algorithms are implemented from scratch

## When to avoid
- you want to build or deploy real deep learning models - use TensorFlow, PyTorch, or similar maintained frameworks
- you need GPU acceleration, modern architectures, or ongoing support

## Facets
- artifact type: library
- maturity: abandoned
- function: machine-learning, deep-learning
- domain: machine-learning, deep-learning
- platform: -
- tags: matlab, octave, neural-networks, deprecated, dbn, autoencoder, cnn

## Member repositories
- rasmusbergpalm/DeepLearnToolbox (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:27.685401+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 2026-08-29T18:25:50.840291+00:00, confidence not recorded.
  - readme: https://github.com/rasmusbergpalm/DeepLearnToolbox (fetched 2026-08-28T04:08:27.685401+00:00, sha 032bfeca77b1)
- Data as of 2026-08-30T08:39:29.467469+00:00.