Spiking Neural Network (SNN) Frameworks
Discover essential SNN frameworks for neuromorphic software development.
- Home /
- Neuromorphic Computing /
- Neuromorphic Software Guide /
- Spiking Neural Network (SNN) Frameworks
SNN Frameworks
Explore essential Spiking Neural Network (SNN) frameworks tailored for the advancement of neuromorphic software development. This guide serves as a comprehensive resource to help researchers and developers navigate and choose frameworks that align with their objectives in the field of neuromorphic computing.
Built on top of PyTorch, used for simulating SNNs, geared towards ML and reinforcement learning.
- Website: https://bindsnet-docs.readthedocs.io/
- Source Code: https://github.com/bindsnet/bindsnet
- License: AGPL-3.0
Open-source DL framework for SNN based on PyTorch, with documentation in English and Chinese.
- Website: https://spikingjelly.readthedocs.io
- Source Code: https://github.com/fangwei123456/spikingjelly
- License: unknown
Focuses on gradient-based training of SNNs, based on PyTorch for GPU acceleration and gradient computation.
- Website: https://snntorch.readthedocs.io
- Source Code: https://github.com/jeshraghian/snntorch
- License: MIT
NIR SupportFree, open-source simulator for SNNs, written in Python, focusing on ease of use and flexibility.
- Website: https://briansimulator.org/
- Source Code: https://github.com/brian-team/brian2
- License: custom
Python package for building, testing, deploying neural networks, supporting many backends for SNN simulation.
- Website: https://nengo.ai
- Source Code: https://github.com/nengo/nengo
- License: custom
NIR Support Hardware SupportExploits bio-inspired neural components, sparse and event-driven, expands PyTorch with primitives for bio-inspired neural components.
- Website: https://norse.github.io/norse/
- Source Code: https://github.com/norse/norse
- License: LGPL-3.0
NIR SupportSimulator for SNN models focusing on dynamics, size, structure of neural systems, not on individual neuron morphology.
- Website: https://www.nest-simulator.org/
- Source Code: https://github.com/nest/nest-simulator
- License: GPL-2.0
Framework for developing neuro-inspired applications, mapping them to neuromorphic hardware.
- Website: https://lava-nc.org/
- Source Code: https://github.com/lava-nc/lava
- License: custom
NIR Support Hardware SupportSimulator for SNN models focusing on networks, not on individual neuron morphology. Optimised for accelerated simulations on computational backends including NVIDIA GPUs.
- Website: https://genn-team.github.io/
- Source Code: https://github.com/genn-team/genn
- License: LGPL-2.1
PyTorch-based DL library for SNNs, focusing on simplicity, fast training, extendability, and vision models.
- Website: https://sinabs.ai
- Source Code: https://github.com/synsense/sinabs
- License: AGPL-3.0
NIR Support Hardware SupportMachine learning library for SNN applications, supports GPU, TPU, CPU acceleration, and neuromorphic compute hardware deployment.
- Website: https://rockpool.ai
- Source Code: https://gitlab.com/synsense/rockpool
- License: AGPL-3.0
NIR Support Hardware SupportGPU-accelerated library for simulating large-scale spiking neural network (SNN) models with high biologically realistic synaptic dynamics.
- Website: https://uci-carl.github.io/CARLsim3/
- Source Code: https://github.com/UCI-CARL/CARLsim6
- License: MIT
Hardware SupportCompact SNN package on DeepMind's Haiku library, based on JAX for JIT compilation on GPUs and TPUs.
- Website: https://spyx.readthedocs.io
- Source Code: https://github.com/kmheckel/spyx
- License: MIT
NIR SupportFramework for machine learning with SNNs built on the GeNN simulator. Focused on ease of use in combination with computational efficiency derived from GeNN.
- Website: https://ml-genn.readthedocs.io/en/latest/
- Source Code: https://github.com/genn-team/ml_genn
- License: LGPL-2.1
