Linear versus nonlinear neural modeling for 2-D pattern recognition

Abstract

This paper compares the classification performance of linear-system- and neural-network-based models in handwritten-digit classification and face recognition. In inputs to a linear classifier, nonlinear inputs are generated based on linear inputs, using different forms of generating products. Using a genetic algorithm, linear and nonlinear inputs to the linear classifier are selected to improve classification performance. Results show that an appropriate set of linear and nonlinear inputs to the linear classifier were selected, improving significantly its classification performance in both problems. It is also shown that the linear classifier reached a classification performance similar to or better than those obtained by nonlinear neural-network classifiers with linear inputs. © 2005 IEEE.

Publication
IEEE Transactions on Systems, Man, and Cybernetics Part A:Systems and Humans
Leo Medina
Leo Medina
Assistant Professor

Leo teaches computer engineering courses at Usach, and his research interests are in the neural engineering and computational neuroscience fields. His work has contributed to understand how nerve fibers respond to electrical stimulation.