发明名称 MULTI-SCALE SPATIO-TEMPORAL NEURAL NETWORK SYSTEM
摘要 Embodiments of the invention relate to a multi-scale spatio-temporal neural network system. One embodiment comprises a neural network including multiple heterogeneous neuron populations that operate at different time scales. Each neuron population comprises at least one digital neuron. Each neuron population further comprises a time scale generation circuit that controls timing for operation of said neuron population, wherein each neuron of said neuron population integrates neuronal firing events at a time scale corresponding to said neuron population. The neural network further comprises a plurality of synapses interconnecting the neurons, wherein each synapse interconnects a neuron with another neuron. At least one neuron receives neuronal firing events from an interconnected neuron that operates at a different time scale.
申请公布号 US2015302294(A1) 申请公布日期 2015.10.22
申请号 US201213562205 申请日期 2012.07.30
申请人 Modha Dharmendra S. 发明人 Modha Dharmendra S.
分类号 G06N3/04 主分类号 G06N3/04
代理机构 代理人
主权项 1. A neural network, comprising: a processor; multiple heterogeneous neuron populations that operate at different time scales, wherein each neuron population comprises: at least one digital neuron; anda time scale generation circuit that controls timing for operation of each neuron of said neuron population by: counting the number of clock steps generated by a clock; andgenerating a time step upon determining that the number of clock steps reaches a time scale threshold parameter of said neuron population, wherein the time step generated triggers each neuron of said neuron population to integrate neuronal firing events at a time scale corresponding to said neuron population; and a plurality of synapses interconnecting the neurons, wherein each synapse interconnects a neuron with another neuron, and wherein at least one neuron receives neuronal firing events from an interconnected neuron that operates at a different time scale.
地址 San Jose CA US