Title :
Pattern recognition using constructive algorithms
Author :
De Sousa, Humberto Costa ; de Carvalho, André
Author_Institution :
LABIC, Sao Paulo Univ., Brazil
Abstract :
This paper aims to analyze the advantages of using constructive algorithms to achieve a functional neural network topology automatically. A constructive neural network simulator, named Kipu, was implemented in order to accomplish the design and analysis of constructive algorithms. Four constructive algorithms were modified to allow the use of real-valued data. Experiments using three pattern recognition tasks were conducted in the Kipu simulator and the results suggest a better functioning of the constructive algorithms compared with the fixed topology MLP network trained with backpropagation algorithm
Keywords :
network topology; neural nets; pattern recognition; simulation; Kipu; constructive algorithms; constructive neural network; network topology; pattern recognition; simulator; Algorithm design and analysis; Analytical models; Artificial neural networks; Backpropagation algorithms; Error analysis; Multilayer perceptrons; Network topology; Neural networks; Neurons; Pattern recognition;
Conference_Titel :
Neural Networks, 1999. IJCNN '99. International Joint Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-5529-6
DOI :
10.1109/IJCNN.1999.836054