Spatial complexity in some class of cellular neural networks
博士 === 國立交通大學 === 應用數學系所 === 96 === This dissertation consists two parts. The first part investigates the complexity of the global set of output patterns for one-dimensional multi-layer cellular neural networks with input; the second part focus on the dense entropy of two-dimensional inhomogeneous c...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | en_US |
Published: |
2008
|
Online Access: | http://ndltd.ncl.edu.tw/handle/40609174901465454499 |
id |
ndltd-TW-096NCTU5507006 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-096NCTU55070062015-10-13T13:51:49Z http://ndltd.ncl.edu.tw/handle/40609174901465454499 Spatial complexity in some class of cellular neural networks 細胞神經網絡的空間複雜度 Chih-Hung Chang 張志鴻 博士 國立交通大學 應用數學系所 96 This dissertation consists two parts. The first part investigates the complexity of the global set of output patterns for one-dimensional multi-layer cellular neural networks with input; the second part focus on the dense entropy of two-dimensional inhomogeneous cellular neural networks with/without input. For the first part, applying labeling to the output space produces a sofic shift space. Two invariants, namely spatial entropy and dynamical zeta function, can be exactly computed by studying the induced sofic shift space. This study gives sofic shift a realization through a realistic model. Furthermore, a new phenomenon, the broken of symmetry of entropy, is discovered in multi-layer cellular neural networks with input. The second part is strongly related to the learning problem (or inverse problem); the necessary and sufficient conditions for the admissibility of local patterns must be characterized. 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, such system exhibits a wide range of phenomena. Song-Sun Lin 林松山 2008 學位論文 ; thesis 68 en_US |
collection |
NDLTD |
language |
en_US |
format |
Others
|
sources |
NDLTD |
description |
博士 === 國立交通大學 === 應用數學系所 === 96 === This dissertation consists two parts. The first part investigates the complexity of the global set of output
patterns for one-dimensional multi-layer cellular neural networks with input; the second part focus on the dense entropy of two-dimensional inhomogeneous cellular neural networks with/without input. For the first part, applying labeling to the output space produces a sofic shift space. Two invariants, namely spatial entropy and dynamical zeta function, can be exactly computed by studying the induced sofic shift space. This study gives sofic shift a realization through a realistic model. Furthermore, a new phenomenon, the broken of symmetry of entropy, is discovered in multi-layer cellular neural networks with input. The second part is strongly related to the learning problem (or inverse problem); the necessary and sufficient conditions for the admissibility of local patterns must be characterized. 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, such system exhibits a wide range of phenomena.
|
author2 |
Song-Sun Lin |
author_facet |
Song-Sun Lin Chih-Hung Chang 張志鴻 |
author |
Chih-Hung Chang 張志鴻 |
spellingShingle |
Chih-Hung Chang 張志鴻 Spatial complexity in some class of cellular neural networks |
author_sort |
Chih-Hung Chang |
title |
Spatial complexity in some class of cellular neural networks |
title_short |
Spatial complexity in some class of cellular neural networks |
title_full |
Spatial complexity in some class of cellular neural networks |
title_fullStr |
Spatial complexity in some class of cellular neural networks |
title_full_unstemmed |
Spatial complexity in some class of cellular neural networks |
title_sort |
spatial complexity in some class of cellular neural networks |
publishDate |
2008 |
url |
http://ndltd.ncl.edu.tw/handle/40609174901465454499 |
work_keys_str_mv |
AT chihhungchang spatialcomplexityinsomeclassofcellularneuralnetworks AT zhāngzhìhóng spatialcomplexityinsomeclassofcellularneuralnetworks AT chihhungchang xìbāoshénjīngwǎngluòdekōngjiānfùzádù AT zhāngzhìhóng xìbāoshénjīngwǎngluòdekōngjiānfùzádù |
_version_ |
1717744689225924608 |