artiomn/awesome-neuromorphic

A curated list of awesome neuromorphic frameworks, libraries, resources, and other things

Awesome Neuromorphic

A curated list of awesome spiking or neuromorphic frameworks, libraries, resources, and other things (i.e. useful robotics simulators and frameworks).

Contents

• Spiking and Neuromorphic Frameworks
• ANN2SNN Converters
• Robotic Toolkits
• Datasets and Dataset Tools
• Computational Neuroscience Software
• Institutes and Groups
  • Motiv NT.
  • The Neuromorphic Vision and Natural Computation Team.
  • Brainchip.
  • SynSense.
• Hardware.

Spiking and Neuromorphic Frameworks

• BindsNET - Python package used for simulating spiking neural networks (SNNs) on CPUs or GPUs using PyTorch Tensor functionality.
• BrainCog - BrainCog is an open source spiking neural network based brain-inspired cognitive intelligence engine for Brain-inspired Artificial Intelligence and brain simulation.
• CARLSim - CARLsim is an efficient, easy-to-use, GPU-accelerated library for simulating large-scale spiking neural network (SNN) models with a high degree of biological detail.
• GeNN - GeNN is a GPU-enhanced Neuronal Network simulation environment based on code generation for Nvidia CUDA.
• Intel LAVA - Software Framework for Neuromorphic Computing from Intel.
• Moose - Multiscale Object-Oriented Simulation Environment. It is designed to simulate neural systems ranging from subcellular components and biochemical reactions to complex models of single neurons, circuits, and large networks.
• Nengo - Python package for building, testing, and deploying spiking neural networks.
• Nest - NEST is a simulator for spiking neural network models that focuses on the dynamics, size and structure of neural systems rather than on the exact morphology of individual neurons.
• NetPyNE - Python package to facilitate the development, simulation, parallelization, analysis, and optimization of biological neuronal networks using the NEURON simulator.
• Neural Circuit Policies - Neural Circuit Policies (NCPs) are designed sparse recurrent neural networks loosely inspired by the nervous system of the organism C. elegans. The goal of this package is to making working with NCPs in PyTorch and keras as easy as possible.
• NEURON - The NEURON simulation environment is used in laboratories and classrooms around the world for building and using computational models of neurons and networks of neurons.
• PeleNet - Reservoir computing framework for Loihi.
• PyNN - Python package for simulator-independent specification of neuronal network models.
• PySNN - Spiking neural network (SNN) framework written on top of PyTorch for efficient simulation of SNNs both on CPU and GPU.
• Sinabs - Open source PyTorch based library, developed to design and implement Spiking Convolutional Neural Networks (SCNNs).
• SPAIC - Spike-based artificial intelligence computing platform.
• spikeflow - Spiking neural networks in tensorflow.
• SpikingJelly - Open-source deep learning framework for Spiking Neural Network (SNN) based on PyTorch.
• SNN Torch - snnTorch is designed to be intuitively used with PyTorch, as though each spiking neuron were simply another activation in a sequence of layers. It is therefore agnostic to fully-connected layers, convolutional layers, residual connections, etc.
• The HBP Neuromorphic Computing Platform - Part of the EBRAINS research infrastructure. The EBRAINS infrastructure is created by the Human Brain Project (HBP).

ANN2SNN Converters

• snn_toolbox - The SNN conversion toolbox (SNN-TB) is a framework to transform rate-based artificial neural networks into spiking neural networks, and to run them using various spike encodings.

Robotic Toolkits

• DART - Dynamic Animation and Robotics Toolkit.

Datasets and Dataset Tools

• Tonic - Tonic is a tool to facilitate the download, manipulation and loading of event-based/spike-based data. It's like PyTorch Vision but for neuromorphic data.

Computational Neuroscience Software

• BrainPy - Framework for computational neuroscience and brain-inspired computation based on the Just-In-Time (JIT) compilation (built on top of JAX, Numba, and other JIT compilers). It provides an integrative ecosystem for brain dynamics programming, including brain dynamics building, simulation, training, analysis, etc.

Institutes and Groups

Motiv NT

AltAI NPU developers.

• motivnt.ru - Official site.

The Neuromorphic Vision and Natural Computation Team

Team, based at the Institut de la Vision in Paris.

• www.neuromorphic-vision.com - Official site.
• GitHub repository - Projects code.

Brainchip

Akida NPU developers.

• brainchip.com - Official site.

SynSense

SynSense focuses on the commercialization of neuromorphic intelligence, based on 20+ years of world-leading experience of University of Zürich and ETH Zürich.

• www.synsense.ai - Official site.

Hardware

• Motiv AltAI - AltAI NPU description page.
• Asprinity AML100 - Analog machine learning chips for the lowest always-on system power.
• End-to-End Implementation of Various Hybrid Neural Networks on a Cross-Paradigm Neuromorphic Chip - Paper.
• Brainchip Akida - Akida NPU.
• Intel Loihi 2 - Intel Loihi 2 NPU.
• Leaky Integrate and Fire (LIF) model implementation for FPGA - FPGA example.

Footnotes

• Awesome Neuroscience - Computational Neuro Science repository.
• Event-based Vision Resources - Big articles list.

awesome-neuromorphic's Issues

Xx