Modular neural networks with applications to pattern profiling problems

Authors:
H. Chris Tseng;Bassam Almogahed
Affiliations:
Department of Computer Science, San Jose State University, One Washington Square, San Jose, CA 95192-0249, USA;Department of Computer Science, San Jose State University, One Washington Square, San Jose, CA 95192-0249, USA
Venue:
Neurocomputing
Year:
2009

Citing 16
Cited 1

A competitive modular connectionist architecture

NIPS-3 Proceedings of the 1990 conference on Advances in neural information processing systems 3
Modular learning

Computational neuroscience
Soft computing in human-related sciences

Soft computing in human-related sciences
Control with words: the modular approach

Information Sciences—Informatics and Computer Science: An International Journal - Special issue computing with words
Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
Intelligent Adaptive Control: Industrial Applications

Intelligent Adaptive Control: Industrial Applications
Modular Neural Network Classifiers: A Comparative Study

Journal of Intelligent and Robotic Systems
Design of structural modular neural networks with genetic algorithm

Advances in Engineering Software
Task decomposition through competition in a modular connectionist architecture

Task decomposition through competition in a modular connectionist architecture
MACLAW: A modular approach for clustering with local attribute weighting

Pattern Recognition Letters - Special issue: Evolutionary computer vision and image understanding
Hybrid Intelligent Systems for Pattern Recognition Using Soft Computing: An Evolutionary Approach for Neural Networks and Fuzzy Systems (Studies in Fuzziness and Soft Computing)

Hybrid Intelligent Systems for Pattern Recognition Using Soft Computing: An Evolutionary Approach for Neural Networks and Fuzzy Systems (Studies in Fuzziness and Soft Computing)
A Nonlinear Mapping for Data Structure Analysis

IEEE Transactions on Computers
Adaptive mixtures of local experts

Neural Computation
Cooperative coevolution of artificial neural network ensembles for pattern classification

IEEE Transactions on Evolutionary Computation
An empirical comparison of combinations of evolutionary algorithms and neural networks for classification problems

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Task decomposition and module combination based on class relations: a modular neural network for pattern classification

IEEE Transactions on Neural Networks

An online self-adaptive modular neural network for time-varying systems

Neurocomputing

Quantified Score

Hi-index	0.01

Visualization

Abstract

We study the feasibility and the performance of modular design concept as applied to pattern profiling problems using artificial neural network. By decomposing the given pattern profiling problem into smaller modules, it is shown that comparable performance can be achieved with improvement on computation and design complexity. A survey of typical modular neural networks shows that large-scale nonlinear problems can alleviate its dimensionality curse with modular technique. Overview of modular neural networks based on how the problem is modularized through various decomposition and subsequent aggregation is given. A pattern recognition problem for aircraft trajectory prediction using NeuroFuzzy learning with a two stage modular learning design is presented. Decoupled data are used to train respective neural network modules. A genetic algorithm is used to aggregate all the learned modules so that it is ready for online pattern recognition purpose. As compared with the non-modular approach, the modular approach offers comparable prediction performance with significantly lower overall computation time. This study validates that modular design is a promising solution for large-scale soft computing problems.