Data

Tools

Indexes

Applications

Experiments

Open Source Science

chaogatenn

Code for gradient based optimization of chaogates paper

https://github.com/nonlinearartificialintelligencelab/chaogatenn

Science Score: 62.0%

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
    Links to: sciencedirect.com
  • ○
    Academic email domains
  • ✓
    Institutional organization owner
    Organization nonlinearartificialintelligencelab has institutional domain (nail.sciences.ncsu.edu)
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (12.1%) to scientific vocabulary

Keywords

choagate machine-learning nonlinear-dynamics optimization
Last synced: 6 months ago · JSON representation ·

Repository

Code for gradient based optimization of chaogates paper

Basic Info
  • Host: GitHub
  • Owner: NonlinearArtificialIntelligenceLab
  • License: mit
  • Language: Jupyter Notebook
  • Default Branch: master
  • Homepage:
  • Size: 5.33 MB
Statistics
  • Stars: 0
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Topics
choagate machine-learning nonlinear-dynamics optimization
Created over 1 year ago · Last pushed about 1 year ago
Metadata Files
Readme License Citation

README.md

chaogatenn

uv Ruff pre-commit bear-ified

Code for gradient based optimization of chaogates paper

This code base is uv compatible and pip installable.

Authors

Anil Radhakrishnan, Sudeshna Sinha, K. Murali ,William L. Ditto

Link to paper

Key Results

  • A gradient-based optimization framework for tuning chaotic systems to match predefined logic gate behavior.
  • Extension of the framework to show simultaneous optimization of multiple logic gates for logic circuits like the half-adder.
  • A demonstration and comparison of the reconfigurability of chaogates across nonlinear map configurations, showing the efficacy of using the same nonlinear system to perform multiple gate operations through parameter tuning

Installation

We recommend using uv to manage python and install the package.

Then, you can simply git clone the repository and run,

bash uv pip install . to install the package with all dependencies.

Usage

The notebooks in the nbs illustrate different extensions and tests of the chaogates framework.

The scripts in the scripts directory are the same as the Diff_chao_config notebooks but with argparsing for easy command line usage for use in batch processing. To run the scripts, you can use the uv run command to run the scripts in the scripts directory. The bash scripts in the scripts directory can be used to run the scripts in batch mode.

The analysis of the statistical run results can be done using the analysis amd plotter notebooks in the nbs directory.

Code References

  • Equinox Pytorch like module for JAX
  • JAX Accelerator-oriented array computation and program transformation
  • Optax Gradient processing and optimization library for JAX

Owner

  • Name: Non Linear Artificial Intelligence Lab
  • Login: NonlinearArtificialIntelligenceLab
  • Kind: organization
  • Location: United States of America

Citation (CITATION.cff) 

cff-version: 1.2.0
title: Gradient based Optimization of Chaogates
message: Please cite this software using these metadata.
type: software
authors:
  - given-names: Anil
    family-names: Radhakrishnan
    email: aradhak5@ncsu.edu
    affiliation: North Carolina State University
    orcid: 'https://orcid.org/0000-0002-8084-9527'
  - given-names: Sudeshna
    family-names: Sinha
    email: sudeshna@iisermohali.ac.in
    affiliation: >-
      Indian Institute of Science Education and Research
      Mohali
    orcid: 'https://orcid.org/0000-0002-1364-5276'
  - given-names: Krishna
    family-names: Murali
    email: kmurali@annauniv.edu
    affiliation: >-
      Department of Physics, Anna University,
      Chennai 600025, India
    orcid: 'https://orcid.org/0000-0001-8055-1117'
  - given-names: William
    name-particle: L
    family-names: Ditto
    email: wditto@ncsu.edu
    affiliation: North Carolina State Universty
    orcid: 'https://orcid.org/0000-0002-7416-8012'
repository-code: 'https://github.com/NonlinearArtificialIntelligenceLab/ChaoGateNN'
abstract: >-
  We present a method for configuring chaogates to replicate standard Boolean logic gate behavior using gradient-based
  optimization. By defining a differentiable formulation of the chaogate encoding, we optimize its tunable parameters to
  reconfigure the chaogate for standard logic gate functions. This novel approach allows us to bring the well-established
  tools of machine learning to optimizing chaogates without the cost of high parameter count neural networks. We further
  extend this approach to the simultaneous optimization of multiple gates for tuning logic circuits. Experimental results
  demonstrate the viability of this technique across different nonlinear systems and configurations, offering a pathway to
  automate parameter discovery for nonlinear computational devices.
keywords:
  - Machine Learning
  - Nonlinear
  - chaogate
  - optimization
license: MIT

GitHub Events

Total
  • Public event: 1
  • Push event: 2
Last Year
  • Public event: 1
  • Push event: 2

Dependencies

pyproject.toml pypi
  • beartype >=0.18.5
  • diffrax >=0.6.0
  • equinox >=0.11.5
  • ipython >=8.26.0
  • jax [cuda12]>=0.4.31
  • jupyter >=1.1.0
  • jupyterlab >=4.2.5
  • matplotlib >=3.9.2
  • optax >=0.2.3
  • ruff >=0.6.3
  • tqdm >=4.66.5
uv.lock pypi
  • 144 dependencies