SpikeSuMNet

![Contributors] ![Forks] ![Issues]

SpikeSuMNet

Report Bug · Request Feature

Table of Contents

1. About The Project
   • Built With
2. Getting Started
   • Prerequisites
   • Installation
3. Roadmap
4. Code
5. Contributing
6. Contact
7. Acknowledgements

About The Project

SpikeSuMNet is a Surprise modulated Spiking neural network project, allowing fast and precise adaptation (learning) within volatile environments. The network implementation is based on the paper Fast adaptive learning in volatile environment

Built With

SpikesumNet is a pytorch-implemented neural network. few other libraries are used for plotting mainly

• Pytorch
• scipy
• plotly
• matplotlib
• tqdm
• jupyter

Getting Started

Installation of the does not require special software but for Python. and python dependencies

Prerequisites

• python to install Python follow the installation guide

Installation

1. Clone the repo

   git clone https://github.com/martinbarry59/SpikeSuMNet.git

2. Install libraries (go to the repository folder)

   pip install -r requirements.txt

Roadmap

See the open issues for a list of proposed features (and known issues).

Code

• Scripts folder: Contains Jupyter notebooks for visualization. Run SpikeMemNet.ipynb runs a full simulation for a 2 transition maze
• Pkg folder: Contains the SpikeSuMNet Python code

Contributing

Contributions are what makes the open-source community such an amazing place to learn, inspire, and create. Any contributions you make are greatly appreciated.

1. Fork the Project
2. Create your Feature Branch (git checkout -b feature/AmazingFeature)
3. Commit your Changes (git commit -m 'Add some AmazingFeature')
4. Push to the Branch (git push origin feature/AmazingFeature)
5. Open a Pull Request

Contact

Project Link: https://github.com/martinbarry59/SpikeSuMNet

Acknowledgements

• Swiss National Science Foundation