Document Detail


A modular neural network architecture for pattern classification based on different feature sets.
MedLine Citation:
PMID:  10651337     Owner:  NLM     Status:  MEDLINE    
Abstract/OtherAbstract:
We propose a novel connectionist method for the use of different feature sets in pattern classification. Unlike traditional methods, e.g., combination of multiple classifiers and use of a composite feature set, our method copes with the problem based on an idea of soft competition on different feature sets developed in our earlier work. An alternative modular neural network architecture is proposed to provide a more effective implementation of soft competition on different feature sets. The proposed architecture is interpreted as a generalized finite mixture model and, therefore, parameter estimation is treated as a maximum likelihood problem. An EM algorithm is derived for parameter estimation and, moreover, a model selection method is proposed to fit the proposed architecture to a specific problem. Comparative results are presented for the real world problem of speaker identification.
Authors:
K Chen; H Chi
Related Documents :
7476467 - Evaluating four diagnostic methods with acute abdominal pain cases.
11264397 - Cytochrome b phylogeny and the taxonomy of great apes and mammals.
19064097 - Clinical analysis of human urine by means of potentiometric electronic tongue.
10624737 - Autoregressive and cepstral analyses of motor unit action potentials.
11385877 - Modeling of a reactive primary clarifier.
920827 - A field and circuit thermodynamics for integrative physiology. i. introduction to the g...
Publication Detail:
Type:  Journal Article; Research Support, Non-U.S. Gov't    
Journal Detail:
Title:  International journal of neural systems     Volume:  9     ISSN:  0129-0657     ISO Abbreviation:  Int J Neural Syst     Publication Date:  1999 Dec 
Date Detail:
Created Date:  2000-02-17     Completed Date:  2000-02-17     Revised Date:  2006-11-15    
Medline Journal Info:
Nlm Unique ID:  9100527     Medline TA:  Int J Neural Syst     Country:  SINGAPORE    
Other Details:
Languages:  eng     Pagination:  563-81     Citation Subset:  IM    
Affiliation:
National Laboratory of Machine Perception and Center for Information Science, Peking University, Beijing, China. chen@cis.pku.edu.cn
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:
Humans
Neural Networks (Computer)*
Pattern Recognition, Automated*

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine


Previous Document:  Recognition of handwritten similar Chinese characters by self-growing probabilistic decision-based n...
Next Document:  Benign diagnosis by image-guided core-needle breast biopsy.