Novel methods and results in training universal multi-nested neurons
Proceedings of the 2002 7th IEEE International Workshop on Cellular Neural Networks and Their Applications - Trang 601-608
Tóm tắt
This paper presents state of the art methods for training compact universal CNN cells (or neurons) to represent arbitrary local Boolean functions. The design tools are analyzed and optimized such that they are capable to provide fast solutions for cells with more than 4 inputs. In particular, it is proved statistically that any arbitrary Boolean function with n=5 inputs (corresponding to a von Neumann CNN neighborhood) admits multinested cell realizations thus confirming a conjecture that was previously proven only for n<5. Several hints are also provided regarding the choice and the influence of various parameters of the design algorithms on the quality of the solution and the speed of finding it.
Từ khóa
#Neurons #Cellular neural networks #Boolean functions #Hypercubes #Equations #Design optimization #Algorithm design and analysis #Logic devices #Reconfigurable logic #ModemsTài liệu tham khảo
10.1007/978-94-009-2975-3_41
ionescu, 2002, High performance distributed architecture for multinested cellular neural network cells design, Proceedings of Twentieth IASTED International ConferenceApplied Informatics (AI 2002), 41
10.1017/CBO9780511754494
goldberg, 1989, Genetic algorithms
kirkpatrick, 1983, Optimization by simulated annealing, Science, 220, 671, 10.1126/science.220.4598.671
10.1016/0893-6080(89)90021-X
matyas, 1965, Random optimization, Automation and Remote Control, 26, 246
julian, 0, A Search Algorithm for the design of Multi-nested Cellular Neural Networks, Proc ISCAS 2002
10.1002/(SICI)1097-007X(199811/12)26:6<593::AID-CTA35>3.0.CO;2-L
10.1142/S021812749900002X