Abstract
Based on two classes of equilibrium equations, a design method for reciprocal Cellular Neural Networks is presented. The local rules denning the task to be accomplished by the network are directly mapped into a set of linear inequalities that bound the solution space of the network parameters for the given problem. All points in the solution space guarantee the correct operation of the network. A solution can be computed by the relaxation method for solving sets of linear inequalities.
Original language | English |
---|---|
Title of host publication | Proceedings - 2nd International Workshop on Cellular Neural Networks and their Applications, CNNA 1992 |
Publisher | Institute of Electrical and Electronics Engineers Inc. |
Pages | 11-16 |
Number of pages | 6 |
ISBN (Electronic) | 0780308751, 9780780308756 |
DOIs | |
State | Published - 1992 |
Externally published | Yes |
Event | 2nd International Workshop on Cellular Neural Networks and their Applications, CNNA 1992 - Munich, Germany Duration: 14 Oct 1992 → 16 Oct 1992 |
Publication series
Name | Proceedings - 2nd International Workshop on Cellular Neural Networks and their Applications, CNNA 1992 |
---|
Conference
Conference | 2nd International Workshop on Cellular Neural Networks and their Applications, CNNA 1992 |
---|---|
Country/Territory | Germany |
City | Munich |
Period | 14/10/92 → 16/10/92 |
Bibliographical note
Publisher Copyright:© 1992 IEEE.