WIT Press


Neurochip Architectural Design For Pattern Recognition And Classification

Price

Free (open access)

Paper DOI

10.2495/HPC000241

Volume

23

Pages

12

Published

2000

Size

1,052 kb

Author(s)

A.N. Kastania and M.P. Bekakos

Abstract

Neurochip architectural design for pattern recognition and classification A.N. Kastania & M.P. Bekakos Department of Informatics, Athens University of Economics & Business, Greece Abstract In this work the construction of a neural network to perform the task of classification from a set of data for which the true classes are known is investigated. Depending upon the knowledge strored in the architecture of an Adaptive Logic Network (ALN) a specialized neurochip is built. The performance of this architecture is evaluated using a challenging medical data set and conclusions are drawn for the expandability of this neurochip for more general cases. 1 Introduction In the attempt to solve the classification problem different types of hybrid neurochips integrating hardware and software components have been proposed. In the MiND[l] system the neuroboard accelerates feedforward networks, radial basis function networks and Kohonen feature maps. Reconfigurable Systolic Array Neur

Keywords