Spiking Neural Network (SNN) Frameworks

SpikingJelly

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

snnTorch

Focuses on gradient-based training of SNNs, based on PyTorch for GPU acceleration and gradient computation.

Maintained by

Jason Eshraghian

NIR Support

View Details

BindsNET

Built on top of PyTorch, used for simulating SNNs, geared towards ML and reinforcement learning.

Brian

Free, open-source simulator for SNNs, written in Python, focusing on ease of use and flexibility.

Nengo

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

Maintained by

Trevor Bekolay

NIR Support Hardware Support

View Details

Norse

Exploits bio-inspired neural components, sparse and event-driven, expands PyTorch with primitives for bio-inspired neural components.

Maintained by

Jens E. Pedersen, Christian Pehle

NIR Support

View Details

Lava

Framework for developing neuro-inspired applications, mapping them to neuromorphic hardware.

NEST

Simulator for SNN models focusing on dynamics, size, structure of neural systems, not on individual neuron morphology.

GeNN

Simulator for SNN models focusing on networks, not on individual neuron morphology. Optimised for accelerated simulations on computational backends including NVIDIA GPUs.

Spyx

Compact SNN package on DeepMind's Haiku library, based on JAX for JIT compilation on GPUs and TPUs.

Sinabs

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

CARLsim

GPU-accelerated library for simulating large-scale spiking neural network (SNN) models with high biologically realistic synaptic dynamics.

mlGeNN

Framework for machine learning with SNNs built on the GeNN simulator. Focused on ease of use in combination with computational efficiency derived from GeNN.

jaxsnn

Event-based training of spiking neural networks with support for BrainScaleS-2 hardware-in-the-loop based on JAX.

Rockpool

Machine learning library for SNN applications, supports GPU, TPU, CPU acceleration, and neuromorphic compute hardware deployment.

Maintained by

Dylan Muir

NIR Support Hardware Support

View Details

hxtorch

Training spiking neural networks with BrainScaleS-2 hardware-in-the-loop support based on PyTorch.

PyNN.brainscales2

Spiking neural networks with complex plasticity on BrainScaleS-2 neuromorphic hardware.