SpikingJelly

Open-source DL framework for SNN based on PyTorch, with documentation in English and Chinese.

Overview

SpikingJelly is an open-source deep learning framework designed for Spiking Neural Networks (SNNs) based on PyTorch. It leverages PyTorch’s user-friendly interface and computational capabilities, including GPU acceleration. This integration makes SpikingJelly an accessible and powerful tool for both researchers and practitioners in the fields of neuroscience and artificial intelligence.

It aims to bring brain-inspired intelligence to neuromorphic chips with high energy efficiency by incorporating neural dynamics and spike properties. SpikingJelly is unique in that it addresses the need for automatic differentiation, parallel computation acceleration, and integration of neuromorphic datasets in the spiking deep learning. The framework provides a full-stack toolkit for preprocessing neuromorphic datasets, constructing deep SNNs, optimizing parameters, and deploying on neuromorphic chips.

Developed by the Multimedia Learning Group, Institute of Digital Media (NELVT) at Peking University, and Peng Cheng Laboratory, SpikingJelly is contributing to the evolution of energy-efficient, spike-based machine intelligence systems. It is a valuable tool for advancing SNN research, offering a blend of accessibility and powerful computational tools for exploring the dynamic world of spiking neural networks.

Can you contribute tutorial guides or case studies?

Get Involved with ONM

Spiking Neural Network (SNN) Library Benchmarks

Spiking Neural Network (SNN) Library Benchmarks

  • Gregor Lenz, Kade Heckel, Sumit Bam Shrestha, Cameron Barker, Jens Egholm Pedersen

Discover the fastest Spiking Neural Network (SNN) frameworks for deep learning-based optimization. Performance, flexibility, and more analyzed in-depth

Efficient Compression for Event-Based Data in Neuromorphic Applications

Efficient Compression for Event-Based Data in Neuromorphic Applications

  • Gregor Lenz, Fabrizio Ottati, Alexandre Marcireau

Discover methods to efficiently encode and store event-based data from high-resolution event cameras, striking a balance between file size and fast retrieval for spiking neural network training.

NorthPole, IBM's latest Neuromorphic AI Hardware

NorthPole, IBM's latest Neuromorphic AI Hardware

  • Fabrizio Ottati

Translating the NorthPole paper from IBM to human language.