Title :
Automatic design of cellular neural networks by means of genetic algorithms: finding a feature detector
Author :
Dellaert, Frank ; Vandewalle, Joos
Author_Institution :
Dept. of Comput. Eng. & Sci., Case Western Reserve Univ., Cleveland, OH, USA
Abstract :
The paper aims to examine the use of genetic algorithms to optimize subsystems of cellular neural network architectures. The application at hand is character recognition: the aim is to evolve an optimal feature detector in order to aid a conventional classifier network to generalize across different fonts. To this end, a performance function and a genetic encoding for a feature detector are presented. An experiment is described where an optimal feature detector is indeed found by the genetic algorithm
Keywords :
cellular neural nets; character recognition; computer vision; encoding; feature extraction; generalisation (artificial intelligence); genetic algorithms; neural net architecture; pattern classification; automatic design; cellular neural network architectures; cellular neural networks; character recognition; conventional classifier network; feature detector; fonts; generalisation; genetic algorithms; genetic encoding; optimal feature detector; performance function; subsystem optimisation; Algorithm design and analysis; Cellular neural networks; Character recognition; Computer vision; Detectors; Genetic algorithms; Image recognition; Neural networks; Neurons; Pixel;
Conference_Titel :
Cellular Neural Networks and their Applications, 1994. CNNA-94., Proceedings of the Third IEEE International Workshop on
Conference_Location :
Rome
Print_ISBN :
0-7803-2070-0
DOI :
10.1109/CNNA.1994.381681
