Science Score: 44.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
    Found CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
    Found .zenodo.json file
  • DOI references
  • Academic publication links
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (9.2%) to scientific vocabulary
Last synced: 6 months ago · JSON representation ·

Repository

Basic Info
  • Host: GitHub
  • Owner: JamieMair
  • License: mit
  • Language: Julia
  • Default Branch: main
  • Size: 352 KB
Statistics
  • Stars: 0
  • Watchers: 1
  • Forks: 0
  • Open Issues: 6
  • Releases: 0
Created over 3 years ago · Last pushed 8 months ago
Metadata Files
Readme License Citation

README.md

SimpleNNs

Dev Build Status

SimpleNNs

SimpleNNs.jl is heavily inspired by SimpleChains.jl, which showed that there is space for micro-optimisations to be very important for small neural networks (see the blog post). This project aims to expand upon SimpleChains.jl by introducing both CPU and GPU support.

As the name suggests, this is not a fully featured neural network library, and most notably, it does not include auto-differentiation capabilities. The goals of this package are the following: 1. To build simple neural network architectures, whose parameters are represented as a simple flat vector. 2. To be able to train and run these neural networks with pre-allocated buffers to avoid memory allocations. 3. To be executable on either the GPU or the CPU.

Currently, there is full support for dense layers with the traditional activation functions: $\text{ReLU}$, $\tanh$ (hyperbolic tangent) and $\sigma$ (logistic sigmoid). Custom loss functions will work on forward passes, but the gradient must be overloaded as detailed in another page of this documentation. Convolutional layers are also supported, with some limitations on parameters such as stride.

Head over to the Getting Started page to see how to use SimpleNNs.jl.

Owner

  • Name: Jamie Mair
  • Login: JamieMair
  • Kind: user
  • Location: Nottingham
  • Company: University Of Nottingham

Citation (CITATION.cff)

cff-version: 0.1.1
message: "If you use this software, please cite it as below."
authors:
  - family-names: Mair
    given-names: Jamie
    orcid: https://orcid.org/0000-0002-1694-8694
title: "SimpleNNs.jl"
version: 0.1.0
date-released: 2022-06-30
url: "https://github.com/JamieMair/SimpleNNs.jl"

GitHub Events

Total
  • Push event: 8
  • Pull request event: 2
  • Create event: 3
Last Year
  • Push event: 8
  • Pull request event: 2
  • Create event: 3

Issues and Pull Requests

Last synced: 9 months ago

All Time
  • Total issues: 12
  • Total pull requests: 17
  • Average time to close issues: 18 days
  • Average time to close pull requests: 4 minutes
  • Total issue authors: 1
  • Total pull request authors: 2
  • Average comments per issue: 0.33
  • Average comments per pull request: 0.0
  • Merged pull requests: 15
  • Bot issues: 0
  • Bot pull requests: 2
Past Year
  • Issues: 0
  • Pull requests: 4
  • Average time to close issues: N/A
  • Average time to close pull requests: 3 minutes
  • Issue authors: 0
  • Pull request authors: 1
  • Average comments per issue: 0
  • Average comments per pull request: 0.0
  • Merged pull requests: 4
  • Bot issues: 0
  • Bot pull requests: 0
Top Authors
Issue Authors
  • JamieMair (12)
Pull Request Authors
  • JamieMair (19)
  • github-actions[bot] (2)
Top Labels
Issue Labels
documentation (1) enhancement (1)
Pull Request Labels

Dependencies

.github/workflows/CI.yml actions
  • actions/checkout v2 composite
  • julia-actions/cache v1 composite
  • julia-actions/julia-buildpkg v1 composite
  • julia-actions/julia-docdeploy v1 composite
  • julia-actions/julia-runtest v1 composite
  • julia-actions/setup-julia v1 composite
.github/workflows/TagBot.yml actions
  • JuliaRegistries/TagBot v1 composite
.github/workflows/CompatHelper.yml actions