Title :
An algorithm for the automatic generation of neural network structures
Author :
Naghan, T. ; Zomaya, Albert Y.
Author_Institution :
Dept. of Electr. & Electron. Eng., Western Australia Univ., Perth, WA, Australia
Abstract :
A backpropagation-based algorithm that dynamically configures the structure of feedforward multilayered neural networks and demonstrates its potential for control applications. The algorithm presents a systematic method for selecting neural network structures according to the complexity of the required mappings. A generate-and-test scheme is employed to evaluate the learning performance of the structure used and modify it accordingly by exploring different alternative structures and selecting the most suitable one. The efficiency of the algorithm is demonstrated using two case studies
Keywords :
backpropagation; feedforward neural nets; neurocontrollers; backpropagation-based algorithm; complexity; control applications; feedforward multilayered neural networks; generate-and-test scheme; learning performance; neural network structures; Artificial neural networks; Backpropagation algorithms; Biological neural networks; Cost function; Feedforward neural networks; Feedforward systems; Heuristic algorithms; Multi-layer neural network; Neural networks; Signal processing algorithms;
Conference_Titel :
Emerging Technologies and Factory Automation, 1993. Design and Operations of Intelligent Factories. Workshop Proceedings., IEEE 2nd International Workshop on
Conference_Location :
Palm Cove-Cairns, Qld.
Print_ISBN :
0-7803-0985-5
DOI :
10.1109/ETFA.1993.396429