RMP-SNN: Residual Membrane Potential Neuron for Enabling Deeper High-Accuracy and Low-Latency Spiking Neural Network

1 code implementation CVPR 2020

We find that performance degradation in the converted SNN stems from using "hard reset" spiking neuron that is driven to fixed reset potential once its membrane potential exceeds the firing threshold, leading to information loss during SNN inference.

BindsNET: A machine learning-oriented spiking neural networks library in Python

1 code implementation4 Jun 2018

In this paper, we describe a new Python package for the simulation of spiking neural networks, specifically geared towards machine learning and reinforcement learning.

OpenAI Gym

SpykeTorch: Efficient Simulation of Convolutional Spiking Neural Networks with at most one Spike per Neuron

1 code implementation6 Mar 2019

Application of deep convolutional spiking neural networks (SNNs) to artificial intelligence (AI) tasks has recently gained a lot of interest since SNNs are hardware-friendly and energy-efficient.

Surrogate Gradient Learning in Spiking Neural Networks

3 code implementations28 Jan 2019

Spiking neural networks are nature's versatile solution to fault-tolerant and energy efficient signal processing.

Temporal Coding in Spiking Neural Networks with Alpha Synaptic Function: Learning with Backpropagation

3 code implementations30 Jul 2019

The timing of individual neuronal spikes is essential for biological brains to make fast responses to sensory stimuli.

Decision Making

Improved robustness of reinforcement learning policies upon conversion to spiking neuronal network platforms applied to ATARI games

3 code implementations26 Mar 2019

Previous studies in image classification domain demonstrated that standard NNs (with ReLU nonlinearity) trained using supervised learning can be converted to SNNs with negligible deterioration in performance.

Atari Games Image Classification +1

S4NN: temporal backpropagation for spiking neural networks with one spike per neuron

1 code implementation21 Oct 2019

In particular, in the readout layer, the first neuron to fire determines the class of the stimulus.

Unsupervised Learning of a Hierarchical Spiking Neural Network for Optical Flow Estimation: From Events to Global Motion Perception

1 code implementation28 Jul 2018

Convolutional layers with input synapses characterized by single and multiple transmission delays are employed for feature and local motion perception, respectively; while global motion selectivity emerges in a final fully-connected layer.

Event-based vision Optical Flow Estimation

Technical report: supervised training of convolutional spiking neural networks with PyTorch

2 code implementations22 Nov 2019

Indeed, the most commonly used spiking neuron model, the leaky integrate-and-fire neuron, obeys a differential equation which can be approximated using discrete time steps, leading to a recurrent relation for the potential.

Convolutional Spiking Neural Networks for Spatio-Temporal Feature Extraction

1 code implementation27 Mar 2020

Spiking neural networks (SNNs) can be used in low-power and embedded systems (such as emerging neuromorphic chips) due to their event-based nature.

Activity Recognition In Videos Event data classification +2