Backpropagation-based learning techniques for deep spiking neural networks: A survey
M Dampfhoffer, T Mesquida… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
With the adoption of smart systems, artificial neural networks (ANNs) have become
ubiquitous. Conventional ANN implementations have high energy consumption, limiting …
ubiquitous. Conventional ANN implementations have high energy consumption, limiting …
Direct learning-based deep spiking neural networks: a review
The spiking neural network (SNN), as a promising brain-inspired computational model with
binary spike information transmission mechanism, rich spatially-temporal dynamics, and …
binary spike information transmission mechanism, rich spatially-temporal dynamics, and …
Spikformer: When spiking neural network meets transformer
We consider two biologically plausible structures, the Spiking Neural Network (SNN) and the
self-attention mechanism. The former offers an energy-efficient and event-driven paradigm …
self-attention mechanism. The former offers an energy-efficient and event-driven paradigm …
Temporal effective batch normalization in spiking neural networks
Abstract Spiking Neural Networks (SNNs) are promising in neuromorphic hardware owing to
utilizing spatio-temporal information and sparse event-driven signal processing. However, it …
utilizing spatio-temporal information and sparse event-driven signal processing. However, it …
Constructing deep spiking neural networks from artificial neural networks with knowledge distillation
Spiking neural networks (SNNs) are well known as the brain-inspired models with high
computing efficiency, due to a key component that they utilize spikes as information units …
computing efficiency, due to a key component that they utilize spikes as information units …
Rmp-loss: Regularizing membrane potential distribution for spiking neural networks
Y Guo, X Liu, Y Chen, L Zhang… - Proceedings of the …, 2023 - openaccess.thecvf.com
Abstract Spiking Neural Networks (SNNs) as one of the biology-inspired models have
received much attention recently. It can significantly reduce energy consumption since they …
received much attention recently. It can significantly reduce energy consumption since they …
Reducing ann-snn conversion error through residual membrane potential
Abstract Spiking Neural Networks (SNNs) have received extensive academic attention due
to the unique properties of low power consumption and high-speed computing on …
to the unique properties of low power consumption and high-speed computing on …
Training spiking neural networks with event-driven backpropagation
Abstract Spiking Neural networks (SNNs) represent and transmit information by
spatiotemporal spike patterns, which bring two major advantages: biological plausibility and …
spatiotemporal spike patterns, which bring two major advantages: biological plausibility and …
Effective surrogate gradient learning with high-order information bottleneck for spike-based machine intelligence
S Yang, B Chen - IEEE transactions on neural networks and …, 2023 - ieeexplore.ieee.org
Brain-inspired computing technique presents a promising approach to prompt the rapid
development of artificial general intelligence (AGI). As one of the most critical aspects …
development of artificial general intelligence (AGI). As one of the most critical aspects …
Exploring loss functions for time-based training strategy in spiking neural networks
Abstract Spiking Neural Networks (SNNs) are considered promising brain-inspired energy-
efficient models due to their event-driven computing paradigm. The spatiotemporal spike …
efficient models due to their event-driven computing paradigm. The spatiotemporal spike …