標題: | ON THE DENSE ENTROPY OF TWO-DIMENSIONAL INHOMOGENEOUS CELLULAR NEURAL NETWORKS |
作者: | Ban, Jung-Chao Chang, Chih-Hung 應用數學系 Department of Applied Mathematics |
關鍵字: | Entropy;learning problem;ICNN |
公開日期: | 1-十一月-2008 |
摘要: | This investigation elucidates the dense entropy of two-dimensional inhomogeneous cellular neural networks (ICNN) with/without input. It is strongly related to the learning problem (or inverse problem); the necessary and sufficient conditions for the admissibility of local patterns must be characterized. For ICNN with/without input, the entropy function is dense in [ 0, log 2] with respect to the parameter space and the radius of the interacting cells, indicating that, in some sense, ICNN exhibit a wide range of phenomena. |
URI: | http://dx.doi.org/10.1142/S0218127408022378 http://hdl.handle.net/11536/8228 |
ISSN: | 0218-1274 |
DOI: | 10.1142/S0218127408022378 |
期刊: | INTERNATIONAL JOURNAL OF BIFURCATION AND CHAOS |
Volume: | 18 |
Issue: | 11 |
起始頁: | 3221 |
結束頁: | 3231 |
顯示於類別: | 期刊論文 |