Sinabs

PyTorch-based DL library for SNNs, focusing on simplicity, fast training, extendability, and vision models.

Sinabs

Overview

Sinabs (Sinabs Is Not A Brain Simulator) is a deep learning library based on PyTorch, specifically designed for spiking neural networks. It focuses on simplicity, fast training, and extendability, demonstrating particularly strong performance with vision models due to its support for weight transfer. The library provides users with an efficient way to convert existing artificial neural networks into spiking neural networks. Its tutorials cover various processes, such as converting an existing ANN or running examples using Backpropagation Through Time (BPTT) with neuromorphic versions of datasets like MNIST.

Sinabs is also equipped with plugins to enhance its functionality, including deploying models to neuromorphic hardware and significantly speeding up the training of feed-forward models. The API reference offers a comprehensive overview of the supported neuron models, the weight transfer API, and other features. The documentation provides insights into getting started with Sinabs, whether you’re exploring the syntax of spiking neural networks or looking to adapt existing neural networks into spiking networks. It is particularly noted for its collaboration with other tools like Rockpool for different types of data or backend needs. Sinabs encourages community engagement with clear contribution guidelines and is maintained by SynSense.

Can you contribute tutorial guides or case studies?

Get Involved with ONM

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.

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

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.