Design and simulation of programmable relational optoelectronic time-pulse coded processors as base elements for sorting neural networks

Abstract

In the paper we show that the biologically motivated conception of time-pulse encoding usage gives a set of advantages (single methodological basis, universality, tuning simplicity, learning and programming et al) at creation and design of sensor systems with parallel input-output and processing for 2D structures hybrid and next generations neurofuzzy neurocomputers. We show design principles of programmable relational optoelectronic time-pulse encoded processors on the base of continuous logic, order logic and temporal waves processes. We consider a structure that execute analog signal extraction, analog and time-pulse coded variables sorting. We offer optoelectronic realization of such base relational order logic element, that consists of time-pulse coded photoconverters (pulse-width and pulse-phase modulators) with direct and complementary outputs, sorting network on logical elements and programmable commutation blocks. We make technical parameters estimations of devices and processors on such base elements by simulation and experimental research: optical input signals power 0.2 -20 uW, processing time 1 -10 us, supply voltage 1 -3 V, consumption power 10 -100 uW, extended functional possibilities, learning possibilities. We discuss some aspects of possible rules and principles of learning and programmable tuning on required function, relational operation and realization of hardware blocks for modifications of such processors. We show that it is possible to create sorting machines, neural networks and hybrid data-processing systems with untraditional numerical systems and pictures operands on the basis of such quasiuniversal hardware simple blocks with flexible programmable tuning.

Convolutional Neural Networks for Early Computer Diagnosis of Child Dysplasia

“…Also, in the study of CNN AlexNet found that the number of layers -25 is not enough to achieve accuracy in the classification of the test group at least up to 80%. In the future, it is proposed to use software and hardware of artificial intelligence, which are discussed in [13,14,15], which will help improve the proposed approach and increase the speed and reliability of diagnosing ultrasound medical images of hip dysplasia.…”