Improvement of the method for uncoupled binary input-output CNN template decomposition
Proceedings of the 2002 7th IEEE International Workshop on Cellular Neural Networks and Their Applications - Trang 459-466
Tóm tắt
This paper proposes an improved method for systematic decomposition of Boolean operators into a sequence of simpler ones. The improvement has two main components: (i) a sufficient condition for decreasing the number of possible child-templates during decomposition; (ii) pointing out the template element, the elimination of which results in the possibly maximum increment of the robustness value of the template. Examples are presented to demonstrate the effectiveness of the proposed method, whose advantages and limitations are also discussed.
Từ khóa
#Cellular neural networks #Robustness #Fault tolerance #Software libraries #Design methodology #Testing #Logic functions #Laboratories #Sufficient conditions #Cellular networksTài liệu tham khảo
güzels, 1994, Recurrent Perceptron Learning for Completely Stable Cellular Neural Networks, Proc IEEE CNNA 94, 177
1997, Analogical and Neural Computing Laboratory
zarandy, 0, Functional Measurements of the First Analog Input/Output CNN Universal Chip
10.1109/81.747197
espejo, 1998, A $64 \times 64$ CNN universal chip with analog and digital I/O, Proc IEEE Int Conf Electronics Circuits and Systems, 203
rosen, 1991, Discrete Mathematics and Its Applications
roska, 1998, CNN Software Library (Templates and Algorithms) Version 7.2
2000, CNN Software Library for ACE4K chip (Templates and Algorithms) Version 1 1
chua, 1997, Cellular Neural Networks: Foundations and Primer
10.1109/82.224318
10.1109/ISCAS.1994.409215
kék, 1999, CNN template decomposition methods tools for implementing analogic algorithms on CNNUM chips
10.1109/82.222815
10.1109/CNNA.1994.381706
10.1109/CNNA.1994.381701
sziranyi, 1994, Texture Classification by CNN and Genetic Learning, Proc Int Conf on Pattern Recognition, iii, 381
10.1109/81.238343
10.1109/81.222795
chandler, 1996, CNN Template Optimization by Adaptive Simulated Annealing, Proc Int Symp Nonlinear Theory Appl, 445
10.1109/31.7600
10.1002/(SICI)1097-007X(199901/02)27:1<5::AID-CTA38>3.0.CO;2-C
földesy, 1998, Fault Tolerant CNN Template Design and Optimatization Based on Chip Measurements, Proc IEEE CNNA-98, 404
10.1002/(SICI)1097-007X(199811/12)26:6<593::AID-CTA35>3.0.CO;2-L
10.1109/CNNA.1992.274355
10.1109/81.563626
10.1109/81.747209
10.1109/CNNA.1996.566606