Obtaining decision boundaries of CSFNN neurons using current mode analog circuitry

Abstract

In this paper, decision boundaries of Conic Section Function Neural Network (CSFNN) neuron obtained with current mode analog circuitry are presented. The designed circuit computes the Radial Basis Function (RBF) and Multilayer Perceptron (MLP) propagation rules on a single hardware to form a CSFNN neuron. Decision boundaries, hyper plane (for MLP) and hyper sphere (for RBF), are special cases of CSFNN Networks depending on the data distribution of a given application. Open and closed decision boundaries and intermediate types of these decision boundaries such as hyperbolas and parabolas for CSFNN have been obtained using designed circuitry. Current mode analog hardware has been designed and the simulations of the neuron circuitry have been realized using Cadence with AMIS 0.5 mu m CMOS transistor model parameters. Simulation results show that the outputs of the circuits are very accurately matched with ideal curve.