Modular neural network programming with genetic optimization

Authors:
Hsing-Chih Tsai;Yong-Huang Lin
Affiliations:
-;-
Venue:
Expert Systems with Applications: An International Journal
Year:
2011

Citing 10
Cited 1

Introduction to artificial neural systems

Introduction to artificial neural systems
Genetic programming: on the programming of computers by means of natural selection

Genetic programming: on the programming of computers by means of natural selection
Genetic algorithms + data structures = evolution programs (3rd ed.)

Genetic algorithms + data structures = evolution programs (3rd ed.)
Modified high-order neural network for invariant pattern recognition

Pattern Recognition Letters
Fuzzy polynomial neural networks for approximation of the compressive strength of concrete

Applied Soft Computing
Prediction and multi-objective optimization of high-strength concrete parameters via soft computing approaches

Expert Systems with Applications: An International Journal
Hybrid high order neural networks

Applied Soft Computing
Predicting strengths of concrete-type specimens using hybrid multilayer perceptrons with center-unified particle swarm optimization

Expert Systems with Applications: An International Journal
High-order neural network structure selection for function approximation applications using genetic algorithms

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
An adaptive high-order neural tree for pattern recognition

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

An optimized instance based learning algorithm for estimation of compressive strength of concrete

Engineering Applications of Artificial Intelligence

Quantified Score

Hi-index	12.05

Visualization

Abstract

This study proposes a modular neural network (MNN) that is designed to accomplish both artificial intelligent prediction and programming. Each modular element adopts a high-order neural network to create a formula that considers both weights and exponents. MNN represents practical problems in mathematical terms using modular functions, weight coefficients and exponents. This paper employed genetic algorithms to optimize MNN parameters and designed a target function to avoid over-fitting. Input parameters were identified and modular function influences were addressed in manner that significantly improved previous practices. In order to compare the effectiveness of results, a reference study on high-strength concrete was adopted, which had been previously studied using a genetic programming (GP) approach. In comparison with GP, MNN calculations were more accurate, used more concise programmed formulas, and allowed the potential to conduct parameter studies. The proposed MNN is a valid alternative approach to prediction and programming using artificial neural networks.