A brain-inspired spiking neural network model with temporal encoding and learning

Abstract Neural coding and learning are important components in cognitive memory system, by processing the sensory inputs and distinguishing different patterns to allow for higher level brain functions such as memory storage and retrieval. Benefitting from biological relevance, this paper presents a spiking neural network of leaky integrate-and-fire (LIF) neurons for pattern recognition. A biologically plausible supervised synaptic learning rule is used so that neurons can efficiently make a decision. The whole system contains encoding, learning and readout. Utilizing the temporal coding and learning, networks of spiking neurons can effectively and efficiently perform various classification tasks. It can classify complex patterns of activities stored in a vector, as well as the real-world stimuli. Our approach is also benchmarked on the nonlinearly separable Iris dataset. The proposed approach achieves a good generalization, with a classification accuracy of 99.63% for training and 92.55% for testing. In addition, the trained networks demonstrate that the temporal coding is a viable means for fast neural information processing.