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 visi...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.展开更多
基金supported in part by the National Natural Science Foundation of China under Grant Nos.62372461,62032001 and 62203457in part by the Key Laboratory of Advanced Microprocessor Chips and Systems.
文摘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.