Title :
Synthesis of artificial neural networks by evolutionary methods
Author :
Ivan, Zelinka ; Pavel, Varacha
Author_Institution :
Tomas Bata Univ., Zlin
Abstract :
This work deals with a problem of synthesis of the artificial neural networks using the evolutional scanning method. The basic task to be solved is to create a symbolic regression algorithm on principles of analytic programming, which will be capable of performing a convenient neural network synthesis. The main motivation here is the computerization of such synthesis and discovering so far unknown solutions.
Keywords :
evolutionary computation; neural nets; regression analysis; analytic programming; artificial neural networks; evolutional scanning method; evolutionary methods; neural network synthesis; symbolic regression algorithm; Algorithm design and analysis; Artificial neural networks; Databases; Evolutionary computation; Expert systems; Functional programming; Network synthesis; Neural networks; Programming profession; Shape;
Conference_Titel :
Database and Expert Systems Applications, 2007. DEXA '07. 18th International Workshop on
Conference_Location :
Regensburg
Print_ISBN :
978-0-7695-2932-5
DOI :
10.1109/DEXA.2007.67
