A structure–time parallel implementation of spike-based deep learning. (May 2019)

• Record Type: Journal Article
• Authors: Wu, Xi; Wang, Yixuan; Tang, Huajin; Yan, Rui
• Is Part Of: Neural networks. Volume 113(2019)
• Page Start: 72
• Page End: 78
• Publication Date: 2019-05
• Subjects: Neuromorphic computing -- Parallel implementation -- Spike-based deep learning -- Deep spiking neural networks; Neural computers -- Periodicals; Neural networks (Computer science) -- Periodicals; Neural networks (Neurobiology) -- Periodicals; Nervous System -- Periodicals; Ordinateurs neuronaux -- Périodiques; Réseaux neuronaux (Informatique) -- Périodiques; Réseaux neuronaux (Neurobiologie) -- Périodiques; Neural computers; Neural networks (Computer science); Neural networks (Neurobiology); Periodicals; 006.32
• DOI: 10.1016/j.neunet.2019.01.010
• Languages: English
• ISSNs: 0893-6080

Abstract

Abstract: Motivated by the recent progress of deep spiking neural networks (SNNs), we propose a structure–time parallel strategy based on layered structure and one-time computation over a time window to speed up the prominent spike-based deep learning algorithm named broadcast alignment. Furthermore, a well-designed deep hierarchical model based on the parallel broadcast alignment is proposed for object recognition. The parallel broadcast alignment achieves a significant 137 × speedup compared to its original implementation on MNIST dataset. The object recognition model achieves higher accuracy than that of the latest spiking deep convolutional neural networks on the ETH-80 dataset. The proposed parallel strategy and the object recognition model will facilitate both the simulation of deep SNNs for studying spiking neural dynamics and also the applications of spike-based deep learning in real-world problems.