A performance analysis of pulse stream neural and fuzzy computing systems

This paper presents an annotated overview of existing hardware implementations of artificial neural systems based on "pulse stream" modulations. Pulse streams are quasi-periodic binary waveforms which convey analog information on waveform timing. The theoretical bases of pulse stream computation are shown for the major techniques, and basic circuits are described for most neural and fuzzy functions. Pulse stream modulations and multiplexing are then analyzed in terms of accuracy, response time, and both power and energy requirements. The performances of the various techniques are compared both with each other, and with those of other analog and digital computing systems. This paper shows that pulse stream systems are comparable with analog systems in terms of size, and comparable with both analog and digital systems in terms of speed. In addition, they offer an increased flexibility if compared to analog systems, and they have both a lower power dissipation and a lower computation energy figure than digital systems.<
>