Title :
A Novel Rotate-and-Fire Digital Spiking Neuron and its Neuron-Like Bifurcations and Responses
Author :
Hishiki, Tetsuya ; Torikai, Hiroyuki
Author_Institution :
Dept. of Syst. Innovation, Osaka Univ., Toyonaka, Japan
fDate :
5/1/2011 12:00:00 AM
Abstract :
A novel rotate-and-fire digital spiking neuron is presented. The digital neuron is a wired system of shift registers and thus it is suited to on-chip learning unlike many other analog spiking neuron models. By adjusting the wiring pattern among the registers, the digital neuron can generate spike trains with various spike patterns and can exhibit related bifurcations. A discrete-continuous hybrid map, which describes the neuron dynamics without any approximation, is derived analytically. Using the hybrid map, it is shown that the digital spiking neuron can mimic typical bifurcation phenomena and various nonlinear responses of biological neurons.
Keywords :
bifurcation; learning (artificial intelligence); neural nets; shift registers; biological neurons; discrete continuous hybrid map; neuron like bifurcations; nonlinear responses; on-chip learning; rotate-and-fire digital spiking neuron; shift registers; Bifurcation; Biological system modeling; Biomembranes; Clocks; Neurons; Wiring; Bifurcation; cellular automaton; field programmable gate array; spiking neuron model; Action Potentials; Artificial Intelligence; Computer Simulation; Mathematical Computing; Mathematical Concepts; Membrane Potentials; Nervous System Physiological Phenomena; Neural Networks (Computer); Neurons; Nonlinear Dynamics; Software Validation;
Journal_Title :
Neural Networks, IEEE Transactions on
DOI :
10.1109/TNN.2011.2116802