Progressive compression and weight reinforcement for spiking neural networks. (2nd March 2022)

• Record Type: Journal Article
• Authors: Elbez, Hammouda; Kamel Benhaoua, Mohammed; Devienne, Philippe; Boulet, Pierre
• Is Part Of: Concurrency and computation. Volume 34:Number 11(2022)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2022-03-02
• Subjects: compression -- dynamic threshold -- neuromorphic computing -- pruning -- spiking neural networks -- unsupervised learning; Parallel processing (Electronic computers) -- Periodicals; Parallel computers -- Periodicals; 004.35
• DOI: 10.1002/cpe.6891
• Languages: English
• ISSNs: 1532-0626

Abstract

Summary: Neuromorphic architectures are one of the most promising architectures to reduce the energy consumption of tomorrow's computers. These architectures are inspired by the behavior of the brain at a fairly precise level and consist of artificial spiking neural networks. To optimize the implementation of these architectures, we propose in this article a novel progressive network compression and reinforcement technique. This technique consists of two functions: progressive pruning and dynamic synaptic weight reinforcement, which we apply after each training batch. The proposed approach delivers a highly compressed network (up to 80% of compression rate) while preserving the network performance when tested with MNIST.