M-LSM:An Improved Multi-Liquid State Machine for Event-Based Vision Recognition  

作　　者：王蕾 郭莎莎 曲连华 田烁 徐炜遐 Lei Wang;Sha-Sha Guo;Lian-Hua Qu;Shuo Tian;Wei-Xia Xu(College of Computer Science and Technology,National University of Defense Technology,Changsha 410073,China)

机构地区：[1]College of Computer Science and Technology,National University of Defense Technology,Changsha 410073,China

出　　处：《Journal of Computer Science & Technology》2023年第6期1288-1299,共12页计算机科学技术学报（英文版）

基　　金：supported in part by the National Natural Science Foundation of China under Grant Nos.62372461,62032001 and 62203457;in part by the Key Laboratory of Advanced Microprocessor Chips and Systems.

摘　　要：Event-based computation has recently gained increasing research interest for applications of vision recogni-tion due to its intrinsic advantages on efficiency and speed.However,the existing event-based models for vision recogni-tion are faced with several issues,such as large network complexity and expensive training cost.In this paper,we propose an improved multi-liquid state machine(M-LSM)method for high-performance vision recognition.Specifically,we intro-duce two methods,namely multi-state fusion and multi-liquid search,to optimize the liquid state machine(LSM).Multi-state fusion by sampling the liquid state at multiple timesteps could reserve richer spatiotemporal information.We adapt network architecture search(NAS)to find the potential optimal architecture of the multi-liquid state machine.We also train the M-LSM through an unsupervised learning rule spike-timing dependent plasticity(STDP).Our M-LSM is evalu-ated on two event-based datasets and demonstrates state-of-the-art recognition performance with superior advantages on network complexity and training cost.

关 键 词：liquid state machine bio-inspired learning classification event-based vision 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]