Simultaneous optimization of neural network function and architecture algorithm

Authors:
Randall S. Sexton;Robert E. Dorsey;Naheel A. Sikander
Affiliations:
Computer Information Systems, Southwest Missouri State University, 901 South National, Springfield, MO;FNC Inc., 606 Van Buren Avenue, Oxford, MS;Computer Information Systems, Southwest Missouri State University, 901 South National, Springfield, MO
Venue:
Decision Support Systems
Year:
2004

Citing 6
Cited 7

What size net gives valid generalization?

Neural Computation
The cascade-correlation learning architecture

Advances in neural information processing systems 2
Genetic algorithms + data structures = evolution programs (3rd ed.)

Genetic algorithms + data structures = evolution programs (3rd ed.)
Toward global optimization of neural networks: a comparison of the genetic algorithm and backpropagation

Decision Support Systems
Designing Neural Networks using Genetic Algorithms

Proceedings of the 3rd International Conference on Genetic Algorithms
The dependence identification neural network construction algorithm

IEEE Transactions on Neural Networks

A neural network application to consumer classification to improve the timing of direct marketing activities

Computers and Operations Research
Employee turnover: a neural network solution

Computers and Operations Research
Machine assessment of neonatal facial expressions of acute pain

Decision Support Systems
Variable step search algorithm for feedforward networks

Neurocomputing
Neural network earnings per share forecasting models: A comparison of backward propagation and the genetic algorithm

Decision Support Systems
Letters: Efficient pruning of multilayer perceptrons using a fuzzy sigmoid activation function

Neurocomputing
Usage of Case-Based Reasoning, Neural Network and Adaptive Neuro-Fuzzy Inference System Classification Techniques in Breast Cancer Dataset Classification Diagnosis

Journal of Medical Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

A major limitation to current artificial neural network (NN) research is the inability to adequately identify unnecessary weights in the solution. If a method were found that would allow unnecessary weights to be identified, decision-makers would gain crucial information about the problem at hand as well as benefit by having a network that was more effective and efficient. The Neural Network Simultaneous Optimization Algorithm (NNSOA) is proposed for supervised training in multilayer feedforward neural networks. We demonstrate with Monte Carlo studies that the NNSOA can be used to obtain both a global solution and simultaneously identify a parsimonious network structure.