Design of structural modular neural networks with genetic algorithm

Authors:
Nan Jiang;Zhiye Zhao;Liqun Ren
Affiliations:
School of Civil and Environmental Engineering, Nanyang Technological University, Nanyang Avenue, Singapore, Singapore;School of Civil and Environmental Engineering, Nanyang Technological University, Nanyang Avenue, Singapore, Singapore;School of Civil and Environmental Engineering, Nanyang Technological University, Nanyang Avenue, Singapore, Singapore
Venue:
Advances in Engineering Software
Year:
2003

Citing 12
Cited 13

Designing neural networks using genetic algorithms

Proceedings of the third international conference on Genetic algorithms
Back-propagation algorithm which varies the number of hidden units

Neural Networks
The cascade-correlation learning architecture

Advances in neural information processing systems 2
Original Contribution: A polynomial time algorithm for the construction and training of a class of multilayer perceptrons

Neural Networks
Radial basis function network configuration using genetic algorithms

Neural Networks
A sequential learning approach for single hidden layer neural networks

Neural Networks
Modular Learning in Neural Networks: A Modularized Approach to Neural Network Classification

Modular Learning in Neural Networks: A Modularized Approach to Neural Network Classification
Introduction to Biological and Artificial Neural Networks for Pattern Recognition

Introduction to Biological and Artificial Neural Networks for Pattern Recognition
Analysis of Pruning in Backpropagation Networks for Artificial and Real Worls Mapping Problems

IWANN '96 Proceedings of the International Workshop on Artificial Neural Networks: From Natural to Artificial Neural Computation
GANNet: A Genetic Algorithm for Optimizing Topology and Weights in Neural Network Design

IWANN '93 Proceedings of the International Workshop on Artificial Neural Networks: New Trends in Neural Computation
A Method of Pruning Layered Feed-Forward Neural Networks

IWANN '93 Proceedings of the International Workshop on Artificial Neural Networks: New Trends in Neural Computation
No free lunch theorems for optimization

IEEE Transactions on Evolutionary Computation

Improving real-parameter genetic algorithm with simulated annealing for engineering problems

Advances in Engineering Software
Biological engineering applications of feedforward neural networks designed and parameterized by genetic algorithms

Neural Networks
Design of ensemble neural network using the Akaike information criterion

Engineering Applications of Artificial Intelligence
Evaluating the process of a genetic algorithm to improve the back-propagation network: A Monte Carlo study

Expert Systems with Applications: An International Journal
Modular neural networks with applications to pattern profiling problems

Neurocomputing
2009 Special Issue: Evolving neural networks for strategic decision-making problems

Neural Networks
Improving real-parameter genetic algorithm with simulated annealing for engineering problems

Advances in Engineering Software
Hybrid structure based on previous knowledge and GA to search the ideal neurons quantity for the hidden layer of MLP-Application in the cold rolling process

Applied Soft Computing
A Radial Basis Function network training algorithm using a non-symmetric partition of the input space - Application to a Model Predictive Control configuration

Advances in Engineering Software
Design of ensemble neural network using entropy theory

Advances in Engineering Software
Fault diagnosis on bottle filling plant using genetic-based neural network

Advances in Engineering Software
A clustering algorithm for radial basis function neural network initialization

Neurocomputing
A systematic estimation model for fraction nonconforming of a wafer in semiconductor manufacturing research

Applied Soft Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

The back-propagation (BP) neural network and the radial basis function (RBF) neural network have been widely used in many engineering applications. In general, the BP neural network can better construct the global approximations to the input-output mapping, whereas an RBF neural network employs the exponentially decaying localized input-output mapping which can effectively model the large variation locally. In this paper, a structural modular neural network, by combining the BP neurons and the RBF neurons at the hidden layer, is proposed to construct a better input-output mapping both locally and globally. The use of genetic algorithm in searching the best hidden neurons makes the structural modular neural network less likely to be trapped in local minima than the traditional gradient-based search algorithms. An analytical function-the peak function is used first to assess the accuracy of the proposed modular approach. The verified approach is then applied to the strength model of concrete under triaxial stresses. The preliminary results show that the modular approach is more accurate than using the RBF neural network or the BP neural network alone.