Title :
Genetic algorithm for CNN template learning
Author :
Kozek, Tibor ; Roska, Tamás ; Chua, Leon O.
Author_Institution :
Dept. of Electr. Eng., California Univ., Berkeley, CA, USA
fDate :
6/1/1993 12:00:00 AM
Abstract :
A learning algorithm for space invariant cellular neural networks (CNNs) is described. Learning is formulated as an optimization problem. Exploration of any specified domain of stable CNNs is possible by the current approach. Templates are derived using a genetic optimization algorithm. Details of the algorithm are discussed and several application results are shown. Using this algorithm, propagation-type and gray-scale-output CNNs can also be designed
Keywords :
genetic algorithms; learning (artificial intelligence); neural nets; CNN template learning; genetic optimization algorithm; gray-scale-output CNNs; learning algorithm; optimization problem; propagation type CNNs; space invariant cellular neural networks; Algorithm design and analysis; Automation; Cellular neural networks; Cost function; Genetic algorithms; Image processing; Neural networks; Programmable logic arrays; Robustness; Stability;
Journal_Title :
Circuits and Systems I: Fundamental Theory and Applications, IEEE Transactions on
