https://github.com/nimavahdat/deepsnn-framework

DeepSNN Framework is an advanced tool for building Spiking Neural Networks, developed for deep learning applications. Tailored for modern neural networks, it features a flexible architecture, convolutional layers, and advanced encoding methods.
https://github.com/nimavahdat/deepsnn-framework

Last synced: about 10 hours ago
JSON representation

DeepSNN Framework is an advanced tool for building Spiking Neural Networks, developed for deep learning applications. Tailored for modern neural networks, it features a flexible architecture, convolutional layers, and advanced encoding methods.

• Host: GitHub
• URL: https://github.com/nimavahdat/deepsnn-framework
• Owner: NimaVahdat
• License: mit
• Created: 2021-08-25T14:58:50.000Z (about 3 years ago)
• Default Branch: main
• Last Pushed: 2024-09-13T17:30:22.000Z (about 2 months ago)
• Last Synced: 2024-09-14T08:25:46.307Z (about 2 months ago)
• Language: Python
• Homepage:
• Size: 85.9 KB
• Stars: 3
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        


  



# DeepSNN Framework

Welcome to DeepSNN, an innovative framework for building Spiking Neural Networks (SNN) designed to cater to the evolving landscape of deep learning. Developed as a project for the Department of Computer Science at the University of Tehran, this framework introduces a fresh approach to constructing deep neural networks with a novel structure.

## Overview

DeepSNN is tailored for deep learning applications, providing a unique architecture for Spiking Neural Networks. It is crafted to seamlessly integrate with modern deep learning practices, offering versatility and adaptability for a variety of projects.

## Features

* **Deep Learning Architecture**: Leverage the power of Spiking Neural Networks with a structure specifically designed for deep learning applications.

* Flexible Neural Model Simulation: Simulate diverse neural models, allowing for in-depth analysis and exploration of different architectures.

* Convolutional and Pooling Capabilities: Use DeepSNN as convolutional and pooling layers within your deep neural network designs.

* Advanced Encoding Methods: Apply cutting-edge encoding methods, including Gabor, DoG, Latency to Intensity, and more, for effective input encoding and filtering.

## Getting Started

Embark on your DeepSNN journey with these simple steps:

* Installation: Clone the repository.

* Configuration: Customize the framework to suit your project's needs by adjusting the configuration files.

* Explore Examples: Delve into a couple of simple example projects provided in the documentation. These examples are crafted to guide you through understanding and mastering the DeepSNN framework.

Contribution Opportunities

DeepSNN welcomes contributions to enhance its functionality and features. Feel free to submit pull requests and engage in discussions on potential improvements.