Title :
Experimental evaluation of a hybrid method for configuring ensemble encoding receptors
Author :
Abdelbar, Ashraf M. ; Hassan, Deena O. ; Tagliarini, Gene A. ; Narayan, Sridhar
Author_Institution :
Dept. of Comput. Sci., American Univ. in Cairo, Egypt
Abstract :
Ensemble encoding is a biologically-motivated, distributed data representation scheme for MLP networks. Multiple overlapping receptive fields are used to enhance the locality of representation. The number, form, and placement of receptive fields has a great impact on performance. In this paper, we explore a technique in which clustering is used to determine receptive field centers, and a variance-based method is used to determine receptive field widths. The relative performance of this hybrid method to other published methods is evaluated experimentally on three benchmark data sets.
Keywords :
data structures; multilayer perceptrons; pattern clustering; distributed data representation scheme; ensemble encoding receptors; multilayer perceptrons networks; multiple overlapping receptive fields; variance-based method; Application software; Auditory system; Biological information theory; Biology; Clustering algorithms; Clustering methods; Computer science; Encoding; Optimization methods; Training data;
Conference_Titel :
Neural Networks, 2005. IJCNN '05. Proceedings. 2005 IEEE International Joint Conference on
Print_ISBN :
0-7803-9048-2
DOI :
10.1109/IJCNN.2005.1555987
