Title :
A constructive learning algorithm for an HME
Author :
Saito, Kazumi ; Nakano, Ryohei
Author_Institution :
NTT Commun. Sci. Lab., Kyoto, Japan
Abstract :
A hierarchical mixtures of experts (HME) model has been applied to several classes of problems, and its usefulness has been shown. However, defining an adequate structure in advance is required and the resulting performance depends on the structure. To overcome this problem, a constructive learning algorithm for an HME is proposed; it includes an initialization method, a training method and an extension method. In our experiments, which used parity problems and a function approximation problem, the proposed algorithm worked much better than the conventional method
Keywords :
function approximation; learning (artificial intelligence); neural nets; constructive learning algorithm; extension method; function approximation problem; hierarchical mixtures of experts model; initialization method; parity problems; training method; Approximation algorithms; Binary trees; Classification tree analysis; Computer networks; Feedforward systems; Function approximation; Input variables; Laboratories; Telephony;
Conference_Titel :
Neural Networks, 1996., IEEE International Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-3210-5
DOI :
10.1109/ICNN.1996.549080
