AUTHOR=Liu Fang , Tao Wentao , Yang Jie , Wu Wei , Wang Jian 

TITLE=STNet: A novel spiking neural network combining its own time signal with the spatial signal of an artificial neural network

JOURNAL=Frontiers in Neuroscience

VOLUME=Volume 17 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/neuroscience/articles/10.3389/fnins.2023.1151949

DOI=10.3389/fnins.2023.1151949

ISSN=1662-453X

ABSTRACT=This paper proposes a novel hybrid network that combines the temporal signal of spiking neural network (SNN) with the spatial signal of artificial neural network (ANN), namely Spatio-Temporal Combined Network (STNet). Inspired by the way of visual cortex in human brain processing visual information, two versions of STNet are designed: a concatenated one (C-STNet) and a parallel one (P-STNet). In C-STNet, ANN simulating primary visual cortex extracts simple spatial information of objects first, and then the obtained spatial information is encoded as spiking time signals for transmitting to the rear SNN which simulates the extrastriate visual cortex to process spikes and classify. In view that information from primary visual cortex reaches extrastriate visual cortex via ventral and dorsal streams, in P-STNet, the parallel combination of ANN and SNN is employed to extract the original spatio-temporal information from samples, and the extracted information is transferred together to a posterior SNN for classification. Experimental results of the two STNets obtained on six small and two large benchmark datasets are compared with eight commonly used approaches, demonstrating that the two STNets can achieve improved performance in terms of accuracy, generalization, stability and convergence.