A Novel Double-Threshold Neural Classifier for Non-Linearly Separable Applications

Abstract

Classification of data finds applications in various engineering and scientific problems. When real-time operation is desired, hardware solutions tend to be more amenable as compared to algorithmic/heuristic solutions. This paper presents a novel current-mode dual-threshold neuron designed and implemented at 32nm CMOS technology node. Subsequently, a current-mode double-threshold classifier is presented which is capable of classifying input patterns of non-linearly separable problems. Thereafter, application of the current-mode dual-threshold neuron in the realization of the XOR function using only a single neural unit is discussed. The proposed neuron as well as both the applications discussed are capable of operating from sub-1V power supplies. Computer simulations using HSPICE yield promising results with the values of delay and power consumption estimated to be lower than existing circuits.