For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Neural Network Model Switching for Efficient Feature Extraction
Keisuke KAMEYAMA Yukio KOSUGI
IEICE TRANSACTIONS on Information and Systems
Publication Date: 1999/10/25
Print ISSN: 0916-8532
Type of Manuscript: PAPER
Category: Image Processing,Computer Graphics and Pattern Recognition
neural network, multilayer perceptron, feature extraction, backpropagation, pruning, model switching,
Full Text: PDF>>
In order to improve the efficiency of the feature extraction of backpropagation (BP) learning in layered neural networks, model switching for changing the function model without altering the map is proposed. Model switching involves map preserving reduction of units by channel fusion, or addition of units by channel installation. For reducing the model size by channel fusion, two criteria for detection of the redundant channels are addressed, and the local link weight compensations for map preservation are formulated. The upper limits of the discrepancies between the maps of the switched models are derived for use as the unified criterion in selecting the switching model candidate. In the experiments, model switching is used during the BP training of a layered network model for image texture classification, to aid its inefficiency of feature extraction. The results showed that fusion and re-installation of redundant channels, weight compensations on channel fusion for map preservation, and the use of the unified criterion for model selection are all effective for improved generalization ability and quick learning. Further, the possibility of using model switching for concurrent optimization of the model and the map will be discussed.