Title :
A comparative study of output representation schemes for multilayer neural networks
Author :
Lu, Bao Liang ; Ito, Koji
Author_Institution :
Bio-Mimetic Control Res. Center, RIKEN, Atsuta, Japan
Abstract :
In this paper, we compare the 1-out-of-N representation scheme with three distributed ones, namely binary, Gray, and simple-sum. We put the emphasis on the training time, learning accuracy, and generalization capability. In order to evaluate the performance of these schemes, three multilayer neural networks (multilayer perceptron, multilayer quadratic perceptron, and multi-sieving network) are used to learn the vowel recognition and image segmentation problems
Keywords :
feedforward neural nets; generalisation (artificial intelligence); image segmentation; learning (artificial intelligence); multilayer perceptrons; performance evaluation; speech recognition; generalization; image segmentation; learning time; multi-sieving network; multilayer neural networks; multilayer perceptron; output representation; vowel recognition; Binary codes; Creep; Multi-layer neural network; Multilayer perceptrons; Neural networks; Nonhomogeneous media; Reflective binary codes; Samarium; Supervised learning;
Conference_Titel :
SICE '95. Proceedings of the 34th SICE Annual Conference. International Session Papers
Conference_Location :
Hokkaido
Print_ISBN :
0-7803-2781-0
DOI :
10.1109/SICE.1995.526962
