| dc.creator (作者) | 蔡瑞煌 | zh_TW |
| dc.creator (作者) | Tsaih,Rua-Huan;Wan,Yat-wah | - |
| dc.date (日期) | 2010-01 | en_US |
| dc.date.accessioned | 6-Oct-2010 11:40:01 (UTC+8) | - |
| dc.date.available | 6-Oct-2010 11:40:01 (UTC+8) | - |
| dc.date.issued (上傳時間) | 6-Oct-2010 11:40:01 (UTC+8) | - |
| dc.identifier.uri (URI) | http://nccur.lib.nccu.edu.tw/handle/140.119/46714 | - |
| dc.description.abstract (摘要) | This study proposes and validates a construction concept for the realization of a real-valued single-hidden layer feed-forward neural network (SLFN) with continuous-valued hidden nodes for arbitrary mapping problems. The proposed construction concept says that for a specific application problem, the upper bound on the number of used hidden nodes depends on the characteristic of adopted SLFN and the observed properties of collected data samples. A positive validation result is obtained from the experiment of applying the construction concept to the m-bit parity problem learned by constructing two types of SLFN network solutions. | - |
| dc.language.iso | en_US | - |
| dc.relation (關聯) | 19th International Conference on Artificial Neural Networks (ICANN2009) | en_US |
| dc.relation (關聯) | Lecture Notes in Computer Science,5768,658-667 | - |
| dc.subject (關鍵詞) | Bound; hidden nodes; single-hidden layer feed-forward neural network; preimage; parity problem | - |
| dc.title (題名) | A Guide for the Upper Bound on the Number of Continuous-Valued Hidden Nodes of a Feed-Forward Network | en_US |
| dc.type (資料類型) | article | en |
| dc.identifier.doi (DOI) | 10.1007/978-3-642-04274-4_68 | en_US |
| dc.doi.uri (DOI) | http://dx.doi.org/10.1007/978-3-642-04274-4_68 | en_US |
