# ivan-vasilev/neuralnetworks

java deep learning algorithms and deep neural networks with gpu acceleration

Repository: https://github.com/ivan-vasilev/neuralnetworks
Canonical: https://ross.abutalabs.com/products/neuralnetworks
Language: Java
License Family: other
Last push: 2017-11-26T03:25:39+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 4748, "days_push": 3202, "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 1236, forks 347 (observed 2026-08-28T04:04:05.096831+00:00)

## What it is
A Java library implementing deep learning algorithms and deep neural network architectures (MLPs, CNNs, RBMs, autoencoders, DBNs) with GPU acceleration via OpenCL and Aparapi. It supports training algorithms like backpropagation and contrastive divergence with greedy layer-wise training.

## Use cases
- train deep neural networks in java
- gpu-accelerated neural network training on jvm
- implement convolutional networks in java
- learn deep learning algorithms from java code
- train autoencoders and deep belief networks
- run backpropagation with dropout on gpu

## When to choose
- you need deep learning in pure Java on the JVM
- you want GPU acceleration via OpenCL without native deep learning stacks
- you want a small, readable codebase for studying deep learning algorithms

## When to avoid
- you need a maintained, production-ready deep learning framework
- you need modern architectures like transformers or recurrent networks
- you need ecosystem support, documentation, or community updates - the project is inactive since 2017

## Facets
- artifact type: library
- maturity: abandoned
- function: deep-learning, machine-learning, gpu-computing
- domain: deep-learning, machine-learning, gpu-computing
- platform: jvm, cross-platform
- tags: neural-networks, opencl, aparapi, convolutional-networks, backpropagation, mnist, java, gpu

## Member repositories
- ivan-vasilev/neuralnetworks (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:05.096831+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 2026-08-30T08:21:58.931260+00:00, confidence not recorded.
  - readme: https://github.com/ivan-vasilev/neuralnetworks (fetched 2026-08-28T04:04:05.096831+00:00, sha 9e594e5e769c)
- Data as of 2026-08-30T08:39:29.467469+00:00.