Data

Tools

Indexes

Applications

Experiments

Open Source Science

RSNNS

RSNNS: Neural Networks in R using the Stuttgart Neural Network Simulator (SNNS)

https://github.com/cbergmeir/rsnns

Science Score: 10.0%

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

  • ○
    CITATION.cff file
  • ○
    codemeta.json file
  • ○
    .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ✓
    Committers with academic emails
    1 of 7 committers (14.3%) from academic institutions
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (4.1%) to scientific vocabulary
Last synced: 11 months ago · JSON representation

Repository

RSNNS: Neural Networks in R using the Stuttgart Neural Network Simulator (SNNS)

Basic Info
  • Host: GitHub
  • Owner: cbergmeir
  • Language: C++
  • Default Branch: master
  • Size: 4.58 MB
Statistics
  • Stars: 27
  • Watchers: 4
  • Forks: 5
  • Open Issues: 11
  • Releases: 0
Created almost 14 years ago · Last pushed over 2 years ago
Metadata Files
Readme

README.md

RSNNS

RSNNS: Neural Networks in R using the Stuttgart Neural Network Simulator (SNNS)

Possible TODOs for the next version:

  • fix crash of Jordan function if called with a matrix

  • fix remaining memory leaks, detected by valgrind, e.g. this one:

==32137== 206,480 (80 direct, 206,400 indirect) bytes in 1 blocks are definitely lost in loss record 2,312 of 2,347 ==32137== at 0x4A081D4: calloc (in /usr/lib64/valgrind/vgpreloadmemcheck-amd64-linux.so) ==32137== by 0x1019F8DD: SnnsCLib::allocMixupArray() (dlvqlearn.cpp:212) ==32137== by 0x101A0B28: SnnsCLib::allocArrays() (dlvqlearn.cpp:942) ==32137== by 0x101A10B7: SnnsCLib::LEARNDLVQ(int, int, float, int, float, int) (dlvqlearn.cpp:1072) ==32137== by 0x101AB52C: SnnsCLib::krcallNetworkFunctionSTD(int, float, int, float, int, int, int) (kernel.cpp:3952) ==32137== by 0x101AB5D6: SnnsCLib::krcallNetworkFunction(int, float, int, float, int, int, int) (kernel.cpp:4019) ==32137== by 0x101D276F: SnnsCLib::kruilearnAllPatterns(float, int, float, int) (krui.cpp:3505) ==32137== by 0x1018347A: SnnsCLib_learnAllPatterns (SnnsCLibWrapper.cpp:1278)

  • Remove printf throughout the code (replace commented printf's with Rprintf, diff of commit May-15h)
  • use the "colorspace" package for heatmaps

  • add JSS paper as vignette

  • Make it possible to pass already trained models in the high-level functions, and use them to initialize the network.

TODOs for a far away future:

  • Implement Softmax/Entropy for elman?
  • Make it possible to implement learning functions in R
  • Implement more sophisticated convergence detection

Owner

  • Login: cbergmeir
  • Kind: user

GitHub Events

Total
Last Year

Committers

Last synced: almost 3 years ago

All Time
  • Total Commits: 176
  • Total Committers: 7
  • Avg Commits per committer: 25.143
  • Development Distribution Score (DDS): 0.483
Past Year
  • Commits: 7
  • Committers: 1
  • Avg Commits per committer: 7.0
  • Development Distribution Score (DDS): 0.0
Top Committers
Name Email Commits
bergmeir b****r@4****e 91
Christoph Bergmeir b****r@n****1 32
Christoph Bergmeir c****r@m****u 22
Christoph Bergmeir c****r@g****m 21
Vitalie Spinu s****t@g****m 6
Seymour Shlien f****3@n****a 3
cbergmeir c****r@d****s 1
Committer Domains (Top 20 + Academic)
decsai.ugr.es: 1 ncf.ca: 1 monash.edu: 1 nenufar8.1: 1

Issues and Pull Requests

Last synced: about 1 year ago

All Time
  • Total issues: 19
  • Total pull requests: 3
  • Average time to close issues: 8 months
  • Average time to close pull requests: 1 day
  • Total issue authors: 16
  • Total pull request authors: 2
  • Average comments per issue: 2.84
  • Average comments per pull request: 0.33
  • Merged pull requests: 1
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 0
  • Pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Issue authors: 0
  • Pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
  • kumarSunny (2)
  • cacoch (2)
  • fawda123 (2)
  • bohmah (1)
  • TamerRizk (1)
  • niceguy1575 (1)
  • lucasvenez (1)
  • cbergmeir (1)
  • mariusbommert (1)
  • heathyates (1)
  • NicolasDenoyelle (1)
  • tarungupta54 (1)
  • suellentz (1)
  • lasoncheng (1)
  • AdDenissen (1)
Pull Request Authors
  • sshlien (2)
  • niceguy1575 (1)
Top Labels
Issue Labels
Pull Request Labels

Packages

  • Total packages: 2
  • Total downloads:
    • cran 2,289 last-month
  • Total docker downloads: 24,578
  • Total dependent packages: 13
    (may contain duplicates)
  • Total dependent repositories: 32
    (may contain duplicates)
  • Total versions: 24
  • Total maintainers: 1
cran.r-project.org: RSNNS

Neural Networks using the Stuttgart Neural Network Simulator (SNNS)

  • Versions: 20
  • Dependent Packages: 13
  • Dependent Repositories: 32
  • Downloads: 2,289 Last month
  • Docker Downloads: 24,578
Rankings
Dependent packages count: 4.6%
Dependent repos count: 4.7%
Downloads: 7.4%
Forks count: 9.6%
Average: 10.2%
Stargazers count: 10.6%
Docker downloads count: 24.2%
Maintainers (1)
c.bergmeir@decsai.ugr.es
Last synced: 11 months ago
conda-forge.org: r-rsnns
  • Versions: 4
  • Dependent Packages: 0
  • Dependent Repositories: 0
Rankings
Dependent repos count: 34.0%
Stargazers count: 43.7%
Average: 43.7%
Forks count: 46.0%
Dependent packages count: 51.2%
Last synced: 11 months ago

Dependencies

RSNNS/DESCRIPTION cran
  • R >= 2.10.0 depends
  • Rcpp >= 0.8.5 depends
  • methods * depends
  • NeuralNetTools * suggests
  • scatterplot3d * suggests