作者: Mokhtar Nibouche , Anthony Pipe , Benjamin Mitchinson , Chris Melhuish , Ian Gilhespy
DOI: 10.1007/11550907_161
关键词: Field-programmable gate array 、 Biological neuron model 、 Artificial neural network 、 Time delay neural network 、 Physical neural network 、 Central nervous system 、 Synapse 、 Synaptic noise 、 Neurophysiology 、 Biological neural network 、 Computer science 、 Artificial intelligence 、 Computer architecture 、 Spiking neural network 、 Nervous system network models 、 Somatosensory system
摘要: A real-time, large scale, leaky-integrate-and-fire neural network processor realized using FPGA is presented. This has been designed, as part of a collaborative project, to investigate and implement biologically plausible models the rodent vibrissae based somatosensory system control robot. An emphasis made on hard real-time performance processor, it be used feedback system. led revision some established modelling protocols in other hardware spiking processors. The underlying neuron model ability synaptic noise inter-neural propagation delays provide greater degree biological plausibility. demonstrated real circuitry independent activity.