Exploiting nonlinear dendritic adaptive computation in training deep Spiking Neural Networks

Inspired by the information transmission process in the brain, Spiking Neural Networks (SNNs) have gained considerable attention due to their event-driven nature. However, as the network structure grows complex, managing the spiking behavior within the network becomes challenging. Networks with exce...

Full description

Saved in:
Bibliographic Details
Published in:Neural networks 2024-02, Vol.170, p.190-201
Main Authors: Shen, Guobin, Zhao, Dongcheng, Zeng, Yi
Format: Article
Language:English
Subjects:
Brain
Cognition
Dendritic Nonlinearity
Dendritic Spatial Gating Module
Dendritic Temporal Adjust Module
Gestures
Membrane Potentials
Neural Networks, Computer
Spiking Neural Networks
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Inspired by the information transmission process in the brain, Spiking Neural Networks (SNNs) have gained considerable attention due to their event-driven nature. However, as the network structure grows complex, managing the spiking behavior within the network becomes challenging. Networks with excessively dense or sparse spikes fail to transmit sufficient information, inhibiting SNNs from exhibiting superior performance. Current SNNs linearly sum presynaptic information in postsynaptic neurons, overlooking the adaptive adjustment effect of dendrites on information processing. In this study, we introduce the Dendritic Spatial Gating Module (DSGM), which scales and translates the input, reducing the loss incurred when transforming the continuous membrane potential into discrete spikes. Simultaneously, by implementing the Dendritic Temporal Adjust Module (DTAM), dendrites assign different importance to inputs of different time steps, facilitating the establishment of the temporal dependency of spiking neurons and effectively integrating multi-step time information. The fusion of these two modules results in a more balanced spike representation within the network, significantly enhancing the neural network’s performance. This approach has achieved state-of-the-art performance on static image datasets, including CIFAR10 and CIFAR100, as well as event datasets like DVS-CIFAR10, DVS-Gesture, and N-Caltech101. It also demonstrates competitive performance compared to the current state-of-the-art on the ImageNet dataset.
ISSN:0893-6080
1879-2782
DOI:10.1016/j.neunet.2023.10.056