VISUAL CLASSIFICATION OF MEDICAL DATA USING MLP MAPPING

In this work we discuss the design of a novel non-linear mapping metho d for visual classification based on multilayer perceptrons (MLP) and assigned class target values. In training the perceptron, one or more target output values for each class in a 2-dimensional space are used. In other words, class membership information is interpreted visually as closeness to target values in a 2D feature space. This mapping is o btained by training the multilayer perceptron (MLP) using class member ship information, input data and judiciously chosen target values. Wei ghts are estimated in such a way that each training feature of the cor responding class is forced to be mapped onto the corresponding 2-dimen sional target value. (C) 1998 Elsevier Science Ltd. All rights reserve d.