DocumentCode :
1733587
Title :
A search algorithm for the design of multinested cellular neural networks
Author :
Julián, Pedro ; Dogaru, Radu ; Haenggi, Martin ; Chua, Leon O.
Author_Institution :
Dept. of Electr. Eng. & Comput. Sci., California Univ., Berkeley, CA, USA
Volume :
1
fYear :
2002
fDate :
6/24/1905 12:00:00 AM
Abstract :
In this paper, we propose a search algorithm that can be used to effectively find multinested cellular neural networks (CNN) implementations for Boolean functions in high dimensional input spaces. For the purposes of this paper, the algorithm is illustrated for the five-dimensional case, although it is completely general and can be applied to find functions with an arbitrary number of inputs. Preliminary results for the 4-bit parameter resolution case are presented.
Keywords :
Boolean functions; cellular neural nets; search problems; Boolean functions; five-dimensional case; high dimensional input spaces; multinested CNN implementations; multinested cellular neural network design; parameter resolution; search algorithm; Algorithm design and analysis; Boolean functions; Cellular networks; Cellular neural networks; Computer networks; Flexible printed circuits; Neural networks; Piecewise linear techniques; USA Councils; Zinc;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Circuits and Systems, 2002. ISCAS 2002. IEEE International Symposium on
Print_ISBN :
0-7803-7448-7
Type :
conf
DOI :
10.1109/ISCAS.2002.1009916
Filename :
1009916
Link To Document :
بازگشت