Neuron type processor modeling using a timed Petri net

The basic operation of a digital neuron is reviewed, and the theory of time Petri nets used for modeling, representation, and analysis of the neuron-type processor (NTP) is reviewed. The timed Petri net is utilized to produce a model for the digital NTP. The neuron-type processor performs input temporal and spatial summation, as well as thresholding. The timed Petri net of the NTP operates asynchronously and sequentially takes on a series of distinct internal states, so that each of these states can concurrently realize a distinct set of steering switching functions depending on the pattern of steering inputs applied to it at the time. This model is structured using several subnets, called essential module units. Depending on the desired number of input dendrites required for the NTP, the essential module units (EMU) are interconnected to produce the required timed Petri net. The timed Petri net and representation facilitates a method of analysis of neural net works containing NTPs prior to hardware implementation