Training multi-layer spiking neural networks with plastic synaptic weights and delays

• Published in: Frontiers in neuroscience Vol. 17; p. 1253830
• Main Author: Wang, Jing
• Format: Journal Article
• Language: English
• Published: Switzerland Frontiers Research Foundation 24.01.2024; Frontiers Media S.A
• Subjects: Algorithms; Back propagation; Firing pattern; Information processing; Learning; Methods; Neural networks; Neurons; Neuroscience; Power consumption; SpikeProp; spiking neural networks; Sports training; supervised learning; synaptic delays; Synaptic plasticity; Synaptic strength; synaptic weights; Weightlifting; spiking neural networks; synaptic weights; synaptic delays; SpikeProp; supervised learning
• ISSN: 1662-453X; 1662-4548; 1662-453X
• DOI: 10.3389/fnins.2023.1253830

Spiking neural networks are usually considered as the third generation of neural networks, which hold the potential of ultra-low power consumption on corresponding hardware platforms and are very suitable for temporal information processing. However, how to efficiently train the spiking neural networks remains an open question, and most existing learning methods only consider the plasticity of synaptic weights. In this paper, we proposed a new supervised learning algorithm for multiple-layer spiking neural networks based on the typical SpikeProp method. In the proposed method, both the synaptic weights and delays are considered as adjustable parameters to improve both the biological plausibility and the learning performance. In addition, the proposed method inherits the advantages of SpikeProp, which can make full use of the temporal information of spikes. Various experiments are conducted to verify the performance of the proposed method, and the results demonstrate that the proposed method achieves a competitive learning performance compared with the existing related works. Finally, the differences between the proposed method and the existing mainstream multi-layer training algorithms are discussed.