Electronic Design, Test and Applications, IEEE International Workshop on (2002)
Christchurch, New Zealand
Jan. 29, 2002 to Jan. 31, 2002
Serge Demidenko , Massey University
Raouf Kh. Sadykhov , Belarussian State University of Informatics and Radioelectronics
Alexey N. Klimovich , Belarussian State University of Informatics and Radioelectronics
Leonid P. Podenok , Institute of Engineering Cybernetics of NAS of Belarus
Maxim E. Vatkin , Institute of Engineering Cybernetics of NAS of Belarus
The automated TV-set aster tuning system capable to control the vertical and horizontal size and position,pin cusion,trapezoid,parallelogramm and tilt has been developed.To solve the problem of non-linearity and non-symmetry approximation the neural network with activation function based on the Volterra series was used.The new algorithm invariant to oscillation of brightness based on neocognitron neural network was applied for processing the grayscale images of integ al circuits.
S. Demidenko, M. E. Vatkin, R. K. Sadykhov, L. P. Podenok and A. N. Klimovich, "Neural Networks to Solve the Problems of Control and Identification," Electronic Design, Test and Applications, IEEE International Workshop on(DELTA), Christchurch, New Zealand, 2002, pp. 318.