Task decomposition and module combination based on class relations: a modular neural network for pattern classification

1999 ◽  
Vol 10 (5) ◽  
pp. 1244-1256 ◽  
Author(s):  
Bao-Liang Lu ◽  
M. Ito
Keyword(s):  
Neural Network ◽  
Pattern Classification ◽  
Class Relations ◽  
Task Decomposition ◽  
Modular Neural Network

A MODULAR NEURAL NETWORK ARCHITECTURE FOR PATTERN CLASSIFICATION BASED ON DIFFERENT FEATURE SETS

1999 ◽  
Vol 09 (06) ◽  
pp. 563-581 ◽  
Author(s):  
KE CHEN ◽  
HUISHENG CHI
Keyword(s):  
Neural Network ◽  
Parameter Estimation ◽  
Pattern Classification ◽  
Network Architecture ◽  
Speaker Identification ◽  
Neural Network Architecture ◽  
Feature Sets ◽  
Modular Neural Network ◽  
Real World Problem ◽  
Comparative Results

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.

Enhancing threshold neural network via suprathreshold stochastic resonance for pattern classification

2021 ◽  
pp. 127387
Author(s):  
Xiaojie Liu ◽  
Lingling Duan ◽  
Fabing Duan ◽  
François Chapeau-Blondeau ◽  
Derek Abbott
Keyword(s):  
Neural Network ◽  
Stochastic Resonance ◽  
Pattern Classification ◽  
Suprathreshold Stochastic Resonance
Sign in / Sign up

Export Citation Format

Share Document