| dc.creator (作者) | 蔡瑞煌 | zh_TW |
| dc.creator (作者) | Tsaih,Rua-Huan | - |
| dc.date (日期) | 1998-07 | en_US |
| dc.date.accessioned | 17-Jan-2009 16:08:13 (UTC+8) | - |
| dc.date.available | 17-Jan-2009 16:08:13 (UTC+8) | - |
| dc.date.issued (上傳時間) | 17-Jan-2009 16:08:13 (UTC+8) | - |
| dc.identifier.uri (URI) | https://nccur.lib.nccu.edu.tw/handle/140.119/27076 | - |
| dc.description.abstract (摘要) | Reasoning Neural Networks (RN) adopts the layered feedforward network structure, and its learning algorithm belongs to the weight-and-structure-change category of learning algorithm. In this paper, we firstly explain that, in the layered feedforward network, the essential characteristic of the mapping between two consecutive layers is the level-adjacent mapping, in which level-adjacent patterns in the previous-layer space are mapped to similar patterns in the latter-layer space. Then, we explain how RN`s learning algorithm handles the undesired predicaments associated with the back propagation learning algorithm. | - |
| dc.format | application/ | en_US |
| dc.language | en | en_US |
| dc.language | en-US | en_US |
| dc.language.iso | en_US | - |
| dc.relation (關聯) | Mathematical and Computer Modelling, 28(2), 37-44 | en_US |
| dc.subject (關鍵詞) | Reasoning neural networks; Activation field; Properly placed; Level-adjacent mapping | - |
| dc.title (題名) | An Explanation of Reasoning Neural Networks | en_US |
| dc.type (資料類型) | article | en |
