An experimental system for optical detection of layout errors of printed circuit boards using learned CNN templates

Cellular neural networks (CNNs) are considered as cellular analog programmable multidimensional processing arrays with distributed logic and memory. The interconnecting weights between the neighboring processing elements are defined by the temperature values. A systematic way to find robust templates is presented. Using the new learning algorithm some templates were found for a CNN based layout design rule checking algorithm. The algorithm has been tested in an experimental system with real life examples. A typical design rule checking of a 432-pixel*164-pixel area takes 8 s of computation time on the CNN hardware accelerator board.<<ETX>>

[1]  Tamás Roska,et al.  Cellular neural networks with nonlinear and delay-type template elements , 1990, IEEE International Workshop on Cellular Neural Networks and their Applications.

[2]  Josef A. Nossek,et al.  Towards a learning algorithm for discrete-time cellular neural networks , 1992, CNNA '92 Proceedings Second International Workshop on Cellular Neural Networks and Their Applications.

[3]  Leon O. Chua,et al.  Genetic algorithm for CNN template learning , 1993 .

[4]  P. Szolgay,et al.  A hardware accelerator board for cellular neural networks: CNN-HAC , 1990, IEEE International Workshop on Cellular Neural Networks and their Applications.

[5]  Lin-Bao Yang,et al.  Cellular neural networks: theory , 1988 .

[6]  Leon O. Chua,et al.  Cellular neural networks: applications , 1988 .

[7]  Tamás Roska,et al.  Genetic algorithm for CNN template learning. (Memo UCB/ERL No. M92/82.) , 1992 .

[8]  Ákos Zarándy,et al.  DUALCOMP dual CNN compiler to CNN-HAC1 board. Version 2.0. 1992. User's guide , 1992 .

[9]  Josef A. Nossek,et al.  Cellular neural network design using a learning algorithm , 1990, IEEE International Workshop on Cellular Neural Networks and their Applications.