학술논문
Harmonic analysis of homogeneous networks
Document Type
Periodical
Author
Source
IEEE Transactions on Neural Networks IEEE Trans. Neural Netw. Neural Networks, IEEE Transactions on. 6(6):1365-1374 Nov, 1995
Subject
Language
ISSN
1045-9227
1941-0093
1941-0093
Abstract
We introduce a generalization of mutually inhibitory networks called homogeneous networks. Such networks have symmetric connection strength matrices that are circulant (one-dimensional case) or block circulant with circulant blocks (two-dimensional case). Fourier harmonics provide universal eigenvectors, and we apply them to several homogeneous examples: k-wta, k-cluster, on/center off/surround, and the assignment problem. We also analyze one nonhomogeneous case: the subset-sum problem. We present the results of 10000 trials on a 50-node k-cluster problem and 100 trials on a 25-node subset-sum problem.ETX