Science Score: 67.0%
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
Found 22 DOI reference(s) in README -
✓Academic publication links
Links to: zenodo.org -
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (4.3%) to scientific vocabulary
Repository
Repository for the nnR package
Basic Info
- Host: GitHub
- Owner: 2shakilrafi
- License: gpl-3.0
- Language: TeX
- Default Branch: master
- Homepage: https://2shakilrafi.github.io/nnR/
- Size: 613 KB
Statistics
- Stars: 2
- Watchers: 1
- Forks: 0
- Open Issues: 0
- Releases: 2
Metadata Files
README.md
nnR
Neural Networks Made Algebraic
This is a repository which implements a certain neural network calculus. This neural network calculus, or atleast the version implemented derives itself mainly from <https://doi.org/10.48550/arXiv.2402.01058>, which in turn is a highly modified version of that found in detail in <https://doi.org/10.1007/s10444-022-09970-2> and <https://doi.org/10.48550/arXiv.2310.20360>.
Our neural network calculus envisions neural networks as an ordered tuple of ordered pairs of $W$ and $b$, weight matrices and bias vectors.
We may compose neural networks as in Definition 2.6 in <https://doi.org/10.48550/arXiv.2402.01058>.
We may stack neural networks as in Definition 2.14 in <https://doi.org/10.48550/arXiv.2402.01058>.
We may take the sum of neural networks as in Definition 2.19 in <https://doi.org/10.48550/arXiv.2402.01058>.
We may take squares and products of neural networks as in Definition 2.24 and Definition 2.25 of respectively of <https://doi.org/10.48550/arXiv.2402.01058>.
We may take powers of neural networks as in Definition 2.26 in <https://doi.org/10.48550/arXiv.2402.01058>.
We may take neural network exponential, sines and cosines, as in Definitions 2.28, 2.29, and 2.30 respectively in <https://doi.org/10.48550/arXiv.2402.01058>.
We may implement the 1-D trapezoidal rule for integration as in Definitions 2.31 and 2.33 in <https://doi.org/10.48550/arXiv.2402.01058>.
Finallly, Norms, Maxima, and a maximum convolution type approximation for 1-D continuous functions is possible as in Definitions 2.35, 2.37, and 2.39 respectively in <https://doi.org/10.48550/arXiv.2402.01058>.
Owner
- Name: Shakil Ahmed Rafi
- Login: 2shakilrafi
- Kind: user
- Location: Arkansas, USA
- Company: University of Arkansas
- Website: https://shakilrafi.online
- Twitter: 2shakilrafi
- Repositories: 5
- Profile: https://github.com/2shakilrafi
I am currently a PhD candidate in Pure Mathematics at the University of Arkansas. My research areas are in PDEs and the use of Artificial Neural Networks.
Citation (CITATION.cff)
# This CITATION.cff file was generated with cffinit.
# Visit https://bit.ly/cffinit to generate yours today!
cff-version: 1.2.0
title: nnR
message: >-
If you use this software, please cite it using the
metadata from this file.
type: software
authors:
- given-names: Shakil
family-names: Rafi
email: sarafi@uark.edu
affiliation: University of Arkansas
orcid: 'https://orcid.org/0000-0003-3791-9697'
identifiers:
- type: doi
value: 10.5281/zenodo.10672209
repository-code: 'https://github.com/2shakilrafi/nnR'
license: GPL-3.0
version: '0.10'
date-released: '2024-02-16'
GitHub Events
Total
- Push event: 1
Last Year
- Push event: 1
Packages
- Total packages: 1
-
Total downloads:
- cran 145 last-month
- Total dependent packages: 0
- Total dependent repositories: 0
- Total versions: 1
- Total maintainers: 1
cran.r-project.org: nnR
Neural Networks Made Algebraic
- Homepage: https://github.com/2shakilrafi/nnR/
- Documentation: http://cran.r-project.org/web/packages/nnR/nnR.pdf
- License: GPL-3
-
Latest release: 0.1.0
published over 2 years ago
Rankings
Maintainers (1)
Dependencies
- testthat >= 3.0.0 suggests