Resources and Tools
Most Recent
Dynex
A digital twin of a physical neuromorphic quantum computing machine, which is operated on hundreds of thousands of GPUs in parallel, delivering unparalleled quantum computing performance at scale for real-world applications....
Dehao Yuan
It is an easy-to-use API for event-based normal flow prediction. Official GitHub repo for "Learning Normal Flow Directly from Event Neighborhoods"....
Tobi Delbruck
Java tools for Address-Event Representation (AER) neuromorphic vision and audio sensor processing. An open source project for real time sensory-motor processing for event-based sensors and systems...
Robert Trelease
Integrating Symbolic Programming and Neuromorphic Modeling with NVIDIA Jetson and GPU-based DNN/ML Systems for Edge Labs...
Dengyu Wu
Neuromorphic paper list, a comprehensive collection of the latest research in the field, is carefully curated and automatically updated every day at 8:00 am GMT to ensure readers have access to the most up-to-date information available....
Prophesee
Prophesee’s latest automotive object detection dataset is some 3.5 TB in size for under 40h of recordings with a single camera....
Application > Autonomous Vehicles
Maqueda, Ana I et al.
A deep neural network approach that unlocks the potential of event cameras on a challenging motion-estimation task: prediction of a vehicle's steering angle....
Nico Messikommer et. al.
This approach introduces a neural network, operating as an agent within the VO pipeline, to make decisions such as keyframe and grid-size selection based on real-time conditions....
Gehrig, Daniel and Scaramuzza, Davide
A hybrid event- and frame-based object detector that preserves the advantages of each modality and thus does not suffer from this trade-off. Our method exploits the high temporal resolution and sparsity of events and the rich but low temporal resolution information in standard images to generate efficient, high-rate object detections, reducing perceptual and computational latency....
Zubic, Nikola et. al.
This workutilize SSMs for temporal aggregation, which enables faster training by either utilizing the S4 model or S5 parallel scans. By their nature, these models allow deployment at different frequencies than those used at training time since they have a learnable timescale parameter....
Pellerito, Roberto et. al. from UZH-RPG
An end-to-end learned image- and event-based VO system. It leverages novel Recurrent, Asynchronous, and Massively Parallel (RAMP) encoders capable of fusing asynchronous events with image data....
Application > Event-based Vision
Dehao Yuan
It is an easy-to-use API for event-based normal flow prediction. Official GitHub repo for "Learning Normal Flow Directly from Event Neighborhoods"....
Tobi Delbruck
Java tools for Address-Event Representation (AER) neuromorphic vision and audio sensor processing. An open source project for real time sensory-motor processing for event-based sensors and systems...
Gehrig, Daniel and Scaramuzza, Davide
A hybrid event- and frame-based object detector that preserves the advantages of each modality and thus does not suffer from this trade-off. Our method exploits the high temporal resolution and sparsity of events and the rich but low temporal resolution information in standard images to generate efficient, high-rate object detections, reducing perceptual and computational latency....
Zubic, Nikola et. al.
This workutilize SSMs for temporal aggregation, which enables faster training by either utilizing the S4 model or S5 parallel scans. By their nature, these models allow deployment at different frequencies than those used at training time since they have a learnable timescale parameter....
Pellerito, Roberto et. al. from UZH-RPG
An end-to-end learned image- and event-based VO system. It leverages novel Recurrent, Asynchronous, and Massively Parallel (RAMP) encoders capable of fusing asynchronous events with image data....
Pietro Bonazzi and others
A neuromorphic methodology for eye tracking, harnessing pure event data captured by a Dynamic Vision Sensor (DVS) camera. The framework integrates a directly trained Spiking Neuron Network (SNN) regression model and leverages a state-of-the-art low power edge neuromorphic processor - Speck, collectively aiming to advance the precision and efficiency of eye-tracking systems....
Andrew C. Freeman
A unified framework for event-based video. Encoder/transcoder/decoder for ADΔER (Address, Decimation, Δt Event Representation) video streams. Includes a transcoder for casting framed video into an ADΔER representation in a manner which preserves the temporal synchronicity of the source, but enables many-frame intensity averaging on a per-pixel basis and extremely high dynamic range....
Zhexiong Wan and others
A deep learning-based dense and continuous optical flow estimation framework from a single image with event streams, which facilitates the accurate perception of high-speed motion....
Tasbolat Taunyazov
NeuTouch is a neuromorphic fingertip tactile sensor that scales well with the number of taxels. The proposed Visual-Tactile Spiking Neural Network (VT-SNN) also enables fast perception when coupled with event sensors. The system is evaluated on two robot tasks: container classification and rotational slip detection....
Bodo Rueckauer and others
An open-source software platform for compiling and running deep spiking neural networks (SNNs) on the Intel Loihi neuromorphic hardware platform. The paper introduces the NxTF API, which provides a simple interface for defining and training SNNs using common deep learning frameworks, and the NxTF compiler, which translates trained SNN models into executable code for the Loihi chip....
Nanyang Technological University
A user-friendly package providing easy access to advanced biosignal processing routines. Researchers and clinicians without extensive knowledge of programming or biomedical signal processing can analyze physiological data with only two lines of code....
Telluride Engineering Workshop Participants - Institute of Neuromorphic Engineering
A set of tools that allow users to decode brain signals into the signals that generated them. It can determine whether the signals come from visual or auditory stimuli, and whether they are measured with EEG, MEG, ECoG or any other neural response for decoding. This toolbox is provided as Matlab and Python code, along with documentation and some sample EEG and MEG data....
Application > Robotics
Nico Messikommer et. al.
This approach introduces a neural network, operating as an agent within the VO pipeline, to make decisions such as keyframe and grid-size selection based on real-time conditions....
Gehrig, Daniel and Scaramuzza, Davide
A hybrid event- and frame-based object detector that preserves the advantages of each modality and thus does not suffer from this trade-off. Our method exploits the high temporal resolution and sparsity of events and the rich but low temporal resolution information in standard images to generate efficient, high-rate object detections, reducing perceptual and computational latency....
Zubic, Nikola et. al.
This workutilize SSMs for temporal aggregation, which enables faster training by either utilizing the S4 model or S5 parallel scans. By their nature, these models allow deployment at different frequencies than those used at training time since they have a learnable timescale parameter....
Pellerito, Roberto et. al. from UZH-RPG
An end-to-end learned image- and event-based VO system. It leverages novel Recurrent, Asynchronous, and Massively Parallel (RAMP) encoders capable of fusing asynchronous events with image data....
UMD PRG
A new event-based vision system that can acquire more environmental information than traditional event cameras. It can maintain a high-informational output while preserving the advantages of event cameras, such as HDR and high temporal resolution....
Robotology
Libraries that handle neuromorphic sensors, such as the dynamic vision sensor, installed on the iCub can be found here, along with algorithms to process the event-based data. Examples include, optical flow, corner detection and ball detection. Demo applications for the iCub robot, and tutorials for running them, include saccading and attention, gaze following a ball, and vergence control....
Loannis Polykretis and others
This package is the Python and ROS implementation of a spiking neural network on Intel's Loihi neuromorphic processor mimicking the oculomotor system to control a biomimetic robotic head....
Guangzhi Tang and others
A PyTorch implementation of the Spiking Deep Deterministic Policy Gradient (SDDPG) framework. The hybrid framework trains a spiking neural network (SNN) for energy-efficient mapless navigation on Intel's Loihi neuromorphic processor....
Collections
Dengyu Wu
Neuromorphic paper list, a comprehensive collection of the latest research in the field, is carefully curated and automatically updated every day at 8:00 am GMT to ensure readers have access to the most up-to-date information available....
Song, Yunlong et al.
A flexible modular quadrotor simulator that supports event camera. Flightmare is composed of two main components: a configurable rendering engine built on Unity and a flexible physics engine for dynamics simulation....
Institute of Neuromorphic Engineering
NIR is a set of computational primitives, shared across different neuromorphic frameworks and technology stacks. The goal of NIR is to decouple the evolution of neuromorphic hardware and software, ultimately increasing the interoperability between platforms and improving accessibility to neuromorphic technologies....
Institute of Neuromorphic Engineering
PyTorch helpers for the Neuromorphic Intermediate Representation (NIR). This is a no frills python package to enable torch based libraries to translate to NIR....
Robotology
Libraries that handle neuromorphic sensors, such as the dynamic vision sensor, installed on the iCub can be found here, along with algorithms to process the event-based data. Examples include, optical flow, corner detection and ball detection. Demo applications for the iCub robot, and tutorials for running them, include saccading and attention, gaze following a ball, and vergence control....
Michael Royal
A guide covering Neuromorphic Computing including the applications, libraries and tools that will make you better and more efficient with Neuromorphic Computing development....
NEUROTECH
Creators and leaders of the Neuromorphic Computing Technology community in Europe, by catalyzing research and collaboration....
Open Neuromorphic
Open Neuromorphic (ONM) provides two things: (i) A curated list of software frameworks to make it easier for everyone to find the tool. (ii)A platform for your code. If you wish to create a new repository or migrate your existing code to ONM, please get in touch with us. You will be made a member of this organisation immediately....
Shikhar Gupta
This is a Python implementation of a hardware efficient spiking neural network. It includes modified learning and prediction rules which could be realised on hardware in an energy efficient way. The aim is to develop a network which could be used for on-chip learning and prediction....
Neuromatch Academy
We have curated a curriculum that spans most areas of computational neuroscience (a hard task in an increasingly big field!). We will expose you to both theoretical modeling and more data-driven analyses. This section will overview the curriculum....
Guillermo Gallego and others
A collection of resources related to event-based vision, a type of computer vision that processes visual data as a stream of events, rather than traditional frame-based methods. The repository contains links to relevant papers, datasets, and tutorials to help further research and development in this field....
Data Sets
Prophesee
Prophesee’s latest automotive object detection dataset is some 3.5 TB in size for under 40h of recordings with a single camera....
Xiao Wang et. al.
A large-scale benchmark dataset for reliable object tracking by fusing RGB and event cameras. The dataset consists of 820 video pairs captured under low illumination, high speed, and background clutter scenarios, and it is divided into a training and a testing subset, each of which contains 500 and 320 videos, respectively....
NatSGD: A Dataset with Speech, Gestures, and Demonstrations for Robot Learning in Natural Human-Robot Interaction
Recent advancements in multimodal Human-Robot Interaction (HRI) datasets have highlighted the fusion of speech and gesture, expanding robots’ capabilities to absorb explicit and implicit HRI insights. However, existing speech-gesture HRI datasets often focus on...
Institute of Neuromorphic Engineering
A tool to facilitate the download, manipulation and loading of event-based/spike-based data. It's like PyTorch Vision but for neuromorphic data!...
IBM Research
This dataset was used to build the real-time, gesture recognition system described in the CVPR 2017 paper titled “A Low Power, Fully Event-Based Gesture Recognition System.” The data was recorded using a DVS128. The dataset contains 11 hand gestures from 29 subjects under 3 illumination conditions and is released under a Creative Commons Attribution 4.0 license....
Garrick Orchard and others
A spiking version of the original frame-based Caltech101 dataset. The N-Caltech101 dataset was captured by mounting the ATIS sensor on a motorized pan-tilt unit and having the sensor move while it views Caltech101 examples on an LCD monitor as shown in the video below....
Applied Brain Research
This dataset contains power benchmarking code for running a simple two-layer, 256-neuron-per-layer neural network keyword spotter on both neuromorphic and conventional hardware devices....
Perception and Robotics Group, University of Maryland
a collection of indoor datasets for motion segmentation and ego-motion estimation gathered with a variety of event-based sensors. The dataset features 6 DoF poses for Camera and Independently Moving Objects updated at 200 Hz, and pixel-wise object masks at 40 Hz. Depth maps and classical camera frames are also available for most sequences....
Machine Learning
Robert Trelease
Integrating Symbolic Programming and Neuromorphic Modeling with NVIDIA Jetson and GPU-based DNN/ML Systems for Edge Labs...
The Neural Simulation Technology Initiative
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. The development of NEST is coordinated by the NEST Initiative....
A compact spiking neural network library built on top of DeepMind's Haiku package, offering the flexibility and extensibility of PyTorch-based frameworks while enabling the extreme perfomance of SNN libraries which implement custom CUDA kernels for their dynamics....
Synsense
A python library for the development and implementation of Spiking Convolutional Neural Networks (SCNNs). The library implements several layers that are spiking equivalents of CNN layers. In addition it provides support to import CNN models implemented in torch conveniently to test their spiking equivalent implementation....
Pietro Bonazzi and others
A neuromorphic methodology for eye tracking, harnessing pure event data captured by a Dynamic Vision Sensor (DVS) camera. The framework integrates a directly trained Spiking Neuron Network (SNN) regression model and leverages a state-of-the-art low power edge neuromorphic processor - Speck, collectively aiming to advance the precision and efficiency of eye-tracking systems....
Neuromorphic Platforms
Dynex
A digital twin of a physical neuromorphic quantum computing machine, which is operated on hundreds of thousands of GPUs in parallel, delivering unparalleled quantum computing performance at scale for real-world applications....
The Neural Simulation Technology Initiative
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. The development of NEST is coordinated by the NEST Initiative....
BindsNET
A deep learning platform built on top of the PyTorch. It is used for the simulation of spiking neural networks (SNNs) and is geared towards machine learning and reinforcement learning....
UMD PRG
A new event-based vision system that can acquire more environmental information than traditional event cameras. It can maintain a high-informational output while preserving the advantages of event cameras, such as HDR and high temporal resolution....
TENNLab
A simple and minimalist—but highly scalable—Field-Programmable Gate Array implementation of neuromorphic computing defined by Univeristy of Tennesse Knoxville (UTK) TENNLab research....
Alexandros Pitilakis and others
Beam Propagation Method (BPM) for planar photonic integrated circuits (PIC), implemented in MATLAB with finite-differences....
Tiffany Hwu and others
A complete neuromorphic solution to outdoor navigation and path planning. The proposed solution is based on a spiking neural network that mimics the biological nervous system of insects. The solution is tested in a real-world scenario and demonstrates promising results in terms of accuracy and efficiency....
Carlos Rios and others
A photonic platform that can combine integrated optics with collocated data storage and processing to enable all-photonic, in-memory computations. By employing nonvolatile photonic elements based on a special phase-change material, it can achieve direct scalar and matrix-vector multiplication, featuring a novel single-shot Write/Erase and a drift-free process....
Paul Merolla and others
A scalable and flexible non–von Neumann architecture that leverages contemporary silicon technology. It includes a 5.4-billion-transistor chip with 4096 neuro synaptic cores interconnected via an intra chip network that integrates 1 million programmable spiking neurons....
Human Brain Project (HBP)
A modeling tool that can generate geometric, kinematic and dynamic models, as well as sensor placement that can be used in the simulation environment of NRP – or any ROS/Gazebo-based environment....
Stanford University
The NeuRRAM neuromorphic chip is a state-of-the-art “compute-in-memory” hybrid circuit that executes computations in memory. It can perform complex cognitive operations without requiring a network connection to a central server. The device is also incredibly adaptable and supports many neural network models and topologies....
Human Brain Project
The Neuromorphic Computing systems SpiNNaker and BrainScaleS allow neuroscientists and engineers to perform experiments with configurable neuromorphic computing systems. The systems are part of the EBRAINS research infrastructure, which is created by the Human Brain Project (HBP)....
Intel
Intel Labs’ second-generation neuromorphic research chip, codenamed Loihi 2, and Lava, is an open-source software framework, which will drive innovation and adoption of neuromorphic computing solutions. Loihi2 is the latest iteration of Intel's Loihi neuromorphic computing platform and is available for partners who want to collaborate with the corporation to explore what it can do....
Sensors > Audio
Juan Pedro Dominguez-Morales
An open-source cross-platform Python module for analyzing and processing spiking information obtained from neuromorphic auditory sensors. It is primarily focused to be used with a NAS, but can work with any other cochlea sensor....
Synsense
A low-power digital SNN inference chip, including a dedicated audio interface. The Xylo-Audio HDK includes an on-board microphone and direct analog audio input for audio processing applications....
iniLabs
An asynchronous event-based silicon cochlea. The board takes stereo audio inputs; the custom chip asynchronously outputs a stream of address-events representing activity in different frequency ranges. As such it is a silicon model of the cochlea, the auditory inner ear....
Sensors > Touch
Institute for Cognitive Systems, Technical University of Munich
A multimodal tactile-sensing module for humanoid robots. By integrating various sensing technologies, this module enables robots to perceive complex tactile information such as force, pressure, temperature, and texture....
Tasbolat Taunyazov
NeuTouch is a neuromorphic fingertip tactile sensor that scales well with the number of taxels. The proposed Visual-Tactile Spiking Neural Network (VT-SNN) also enables fast perception when coupled with event sensors. The system is evaluated on two robot tasks: container classification and rotational slip detection....
Debarun Sengupta and others
An approach entailing carbon nanofiber–polydimethylsiloxane composite-based piezoresistive sensors, coupled with spiking neural networks, to mimic skin-like sensing....
Luke Osborn and others
A multilayered electronic dermis (e-dermis) with properties based on the behavior of mechanoreceptors and nociceptors to provide neuromorphic tactile information for an amputee....
Sensors > Vision
UMD PRG
A new event-based vision system that can acquire more environmental information than traditional event cameras. It can maintain a high-informational output while preserving the advantages of event cameras, such as HDR and high temporal resolution....
Synsense
Speck is a neuromorphic vision system-on-chip, combining an event-based vision sensor with spiking CNN cores for inference on vision tasks. The Speck HDK includes an interchangeable lens, and full resources for developing neuromorphic vision applications....
Sony and Prophesee
Metavision Sensing and Software offer all the resources to work with event-driven cameras. The sensational IMX636ES is the new event-driven sensor created by a collaboration between Sony and PROPHESEE. The Metavision software offers 95 algorithms, 67 code samples and 11 ready-to-use applications to be used with this new generation of cameras....
Inivation AG
A high-resolution event-based sensors that only output event streams. Compared to the DAVIS series, it can provide (640 x 480) resolution, but is not able to output greyscale images....
Inivation AG
A dynamic and active pixel vision sensor (DAVIS), which addresses the lack of greyscale output of the DVXplorer series by utilising asynchronous DVS events and synchronous global shutter frames concurrently. The active pixel sensor (APS) circuits and the DVS circuits within a pixel share a single photodiode....
Software and Tools
Tobi Delbruck
Java tools for Address-Event Representation (AER) neuromorphic vision and audio sensor processing. An open source project for real time sensory-motor processing for event-based sensors and systems...
SpikingJelly is a comprehensive, open-source deep learning framework designed for Spiking Neural Networks (SNNs), built on top of PyTorch. It provides a robust set of tools and features for researchers, developers, and enthusiasts looking to harness the power of SNNs for neuromorphic computing and beyond....
A compact spiking neural network library built on top of DeepMind's Haiku package, offering the flexibility and extensibility of PyTorch-based frameworks while enabling the extreme perfomance of SNN libraries which implement custom CUDA kernels for their dynamics....
BindsNET
A deep learning platform built on top of the PyTorch. It is used for the simulation of spiking neural networks (SNNs) and is geared towards machine learning and reinforcement learning....
Lava
Dynamic Neural Fields (DNF) are neural attractor networks that generate stabilized activity patterns in recurrently connected populations of neurons. These activity patterns form the basis of neural representations, decision making, working memory, and learning....
uzh-rpg
Introduce state-space models (SSMs) with learnable timescale parameters to event-based vision. This design adapts to varying frequencies without the need to retrain the network at different frequencies....
Synsense
Samna is the developer interface to the SynSense toolchain and run-time environment for interacting with all SynSense devices....
Synsense
A python library for the development and implementation of Spiking Convolutional Neural Networks (SCNNs). The library implements several layers that are spiking equivalents of CNN layers. In addition it provides support to import CNN models implemented in torch conveniently to test their spiking equivalent implementation....
UMD PRG
A new event-based vision system that can acquire more environmental information than traditional event cameras. It can maintain a high-informational output while preserving the advantages of event cameras, such as HDR and high temporal resolution....
Pietro Bonazzi and others
A neuromorphic methodology for eye tracking, harnessing pure event data captured by a Dynamic Vision Sensor (DVS) camera. The framework integrates a directly trained Spiking Neuron Network (SNN) regression model and leverages a state-of-the-art low power edge neuromorphic processor - Speck, collectively aiming to advance the precision and efficiency of eye-tracking systems....
Andrew C. Freeman
A unified framework for event-based video. Encoder/transcoder/decoder for ADΔER (Address, Decimation, Δt Event Representation) video streams. Includes a transcoder for casting framed video into an ADΔER representation in a manner which preserves the temporal synchronicity of the source, but enables many-frame intensity averaging on a per-pixel basis and extremely high dynamic range....
Man Yao et al.
A general Transformer-based SNN architecture, whose goals are: (1) Lower-power, supports the spike-driven paradigm that there is only sparse addition in the network; (2) Versatility, handles various vision tasks; (3) High-performance, shows advantages over CNN-based SNNs; (4) Meta-architecture, inspires future next-generation Transformer-based neuromorphic chip designs....
Xuerui Qiu et al.
A plug-and-play module that leverages the multi-dimensional gated attention unit to efficiently encode inputs into powerful representations before feeding them into the SNN architecture....
Juan Pedro Dominguez-Morales
An open-source cross-platform Python module for analyzing and processing spiking information obtained from neuromorphic auditory sensors. It is primarily focused to be used with a NAS, but can work with any other cochlea sensor....
Yuhuang Hu
Low-level Python APIs for Accessing Neuromorphic Devices. A combination of a Pythonic libcaer and a light-weight "ROS". PyAER serves as an agile package that focus on fast development and extensibility....
brainpy
A flexible, efficient, and extensible 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)....
brain-team
A free, open source simulator for spiking neural networks. It is written in the Python programming language and is available on almost all platforms....
BindsNET
A spiking neural network simulation library geared towards the development of biologically inspired algorithms for machine learning. This package is used as part of ongoing research on applying SNNs to machine learning (ML) and reinforcement learning (RL) problems in the Biologically Inspired Neural & Dynamical Systems (BINDS) lab....
Zhexiong Wan and others
A deep learning-based dense and continuous optical flow estimation framework from a single image with event streams, which facilitates the accurate perception of high-speed motion....
TU-Delft
cuSNN is a C++ library that enables GPU-accelerated simulations of large-scale Spiking Neural Networks (SNNs)....
Lava
A library of deep learning tools within Lava that support offline training, online training and inference methods for various Deep Event-Based Networks....
Prophesee
An open source project associated with Metavision SDK. It enables anyone to get a better understanding of event-based vision, directly interact with events and build their own applications or plugins....
Institute of Neuromorphic Engineering
A tool to facilitate the download, manipulation and loading of event-based/spike-based data. It's like PyTorch Vision but for neuromorphic data!...
Norse
Norse expands PyTorch with primitives for bio-inspired neural components, bringing two advantages: a modern and proven infrastructure based on PyTorch and deep learning-compatible spiking neural network components....
Andrzej Kucik and Gabriele Meoni
A package that deploy spiking neural networks (SNN) in land cover and land use classification tasks. In particular, a VGG-16 -based artificial neural network (ANN) classifier is converted into an SNN using KerasSpiking. After fine-tuning of the converted model, the accuracy depreciation as well as a potential improvement in the energy consumption are compared on selected hardware platforms....
Guillaume Bellec and others
A tensorflow 1.12 library and a tutorial to train a recurrent spiking neural networks. This model uses a method of network rewiring to keep a sparse connectivity during training, which is called DEEP-R....
SynSense
An open-source Python package for simulating, training and deploying spiking neural network applications. Includes simulations and deployment to SynSense hardware....
Guillaume Bellec and others
A tensorflow 1.12 library and a tutorial to train a Long short-term memory Spiking Neural Network. The proposed model uses a method of network rewiring to keep a sparse connectivity during training, which is called DEEP R....
Peter Blouw and others
A power benchmarking code for running a simple two-layer, 256 neuron per layer neural network keyword spotter on both neuromorphic and conventional hardware devices. On conventional devices a Tensorflow version of the keyword spotter is used, while on neuromorphic devices (Loihi), an architecturally identical Nengo version is used....
Perception and Robotics Group, UMD
A project that explores the use of event cameras in dynamic obstacle dodging tasks. Unlike traditional cameras. The project uses deep learning techniques to train a neural network to predict the trajectory of moving obstacles and generate control signals for a drone to avoid collisions in real-time....
IBM
An open source Python toolkit for exploring and using the capabilities of in-memory computing devices in the context of artificial intelligence. The toolkit is fully GPU accelerated and can be used to conveniently estimate the impact of material properties and non-idealities of future analog technology on the accuracy for arbitrary ANNs....
Zhenhua Zhu and others
A behavior-level modeling tool for designing and simulating memristor-based neuromorphic computing systems. MNSIM 2.0 provides a high-level model of the memristive devices and their circuits, allowing for efficient and accurate simulation of large-scale systems....
Prophesee
A C++ and Python SDK for event-based data processing. It includes algorithms available via APIs, code samples and documentation allowing you to develop event-based applications ready to go to production. The algorithms are written in C++ for performance reasons, but are also provided through a Python API through bindings of the C++ code....
Laboratory for Emerging Devices and Circuits, Georgia Institute of Technology
An integrated framework to emulate the deep neural networks (DNN) inference performance or on-chip training performance on the hardware accelerator based on near-memory computing or in-memory computing architectures....
Applied Brain Research
A simulator for Nengo models. That means it takes a Nengo network as input and allows the user to simulate that network using some underlying computational framework (in this case, TensorFlow). In practice, this means that the code for constructing a Nengo model is exactly the same as it would be for the standard Nengo simulator....
Applied Brain Research
A Python library for building and simulating large-scale neural models. Nengo can create sophisticated spiking and non-spiking neural simulations with sensible defaults in a few lines of code. In addition, Nengo is highly versatile. You can define your own neuron types and learning rules, drive robots, and even simulate your model on a completely different neural simulator or neuromorphic hardware....
Riccardo Massa and others
An efficient spiking neural network for recognizing gestures with a DVS Camera on the Loihi neuromorphic processor. It can be used for analyzing the DNN-to-SNN conversion through SNNToolbox, and the codes for pre-processing the DvsGesture dataset to make it possible to train in the DNN domain....
SpiNNaker - University of Manchester
SpiNNaker is a novel computer architecture inspired by the working of the human brain. A SpiNNaker machine is a massively parallel computing platform, targeted toward three main areas of research: Neuroscience, Robotics, and Computer Vision. This package provides standard code for PyNN implementations for SpiNNaker....
Jason Eshraghian
A Python package for performing gradient-based learning with spiking neural networks. It extends the capabilities of PyTorch, taking advantage of its GPU accelerated tensor computation and applying it to networks of spiking neurons....
Friedemann Zenke
An open-source project that provides a PyTorch-based library for deep learning with spiking neural networks (SNNs). The library aims to make it easy to train and evaluate SNNs. This library provides a range of tools and functionality to help researchers and practitioners work with SNNs in a flexible and intuitive way, including support for common SNN models and training algorithms....
Intel
An open-source software framework for developing neuro-inspired applications and mapping them to neuromorphic hardware. Includes various useful packages including a Neuromorphic Constrained Optimization Library....