A Modified Spiking Neuron that Involves Derivative of the State Function at Firing Time

摘要

In usual spiking neural networks, the real world information is interpreted as spike time. A spiking neuron of the spiking neural network receives input vector of spike times, and activates a state function x(t) by increasing the time t until the value of x(t) reaches certain threshold value at a firing time t a. And t a is the output of the spiking neuron. In this paper we propose, and investigate the performance of, a modified spiking neuron, of which the output is a linear combination of the firing time t a and the derivative x′(t a). The merit of the modified spiking neuron is shown by numerical experiments for solving some benchmark problems: The computational time of a modified spiking neuron is a little greater than that of a usual spiking neuron, but the accuracy of a modified spiking neuron is almost as good as a usual spiking neural network with a hidden layer.