Nengo

Python package for building, testing, deploying neural networks, supporting many backends for SNN simulation.

Nengo

Overview

Nengo, also known as “Brain Maker”, is a versatile open-source Python package designed for building, testing, and applying neural networks, and it supports many backends for spiking neural networks (SNNs). Developed and maintained by Trevor Bekolov, Nengo is accompanied by comprehensive and extensive documentation that covers all of its plugins and example implementations of Nengo plugins for newcomers. The framework boasts a large and passionate community that supports and contributes to Nengo.

Nengo is unique for its seamless compatability with many different applications FPGA boards, Intel’s Loihi chip, TensorFlow, an HTML-5 interactive visualizer, and PyTorch to name a few. The project supports a wide range of neuron types and is highly adaptable, allowing users to deploy various cognitive and perceptual models on both conventional and neuromorphic hardware. With its wide variety of applications, Nengo provides a user-friendly syntax and high-level abstractions, making it accessible for both researchers and newcomers to deep learning and neural networks.

Can you contribute tutorial guides or case studies?

Get Involved with ONM

  • Website: https://nengo.ai
  • Source Code: https://github.com/nengo/nengo
  • Dependencies:
  • Field of Application: Machine Learning, Neuroscience
  • License: custom
  • Supports Hardware: true
  • Supports NIR: true
  • Language: Python
  • Maintainer: Trevor Bekolay
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

Digital Neuromorphic Hardware Read List

Digital Neuromorphic Hardware Read List

  • Fabrizio Ottati

Stay up-to-date with cutting-edge digital hardware designs for neuromorphic applications. Explore recent research on power-efficient event-driven spiking neural networks and state-of-the-art processors like TrueNorth and Loihi.

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.