完整後設資料紀錄
DC 欄位語言
dc.contributor.authorKamimura, Ryotaro
dc.date.accessioned2009-08-23T04:40:15Z
dc.date.accessioned2020-05-25T06:25:06Z-
dc.date.available2009-08-23T04:40:15Z
dc.date.available2020-05-25T06:25:06Z-
dc.date.issued2006-10-20T06:30:45Z
dc.date.submitted1998-12-17
dc.identifier.urihttp://dspace.lib.fcu.edu.tw/handle/2377/2057-
dc.description.abstractIn this paper, new information called structural information is proposed. Structural information is composed of two types of information: The first order information and the second order information. The first and second order information represent information on deviation from the equiprobable distribution and the independence respectively. We have so far dealt with total information to be stored in neural networks. However, by introducing structural information, we can control appropriate types of information, depending on methods and problems. In other words, we can control information, taking into account the quality as well as the quantity of information. We applied the structural information to information content in input-hidden connections and hidden units. Then is was applied to XOR problem to show how the structural information control affects the simplification of network architectures. In addition, we applied the methods to language acquisition problems complex enough to test the performance. Experimental results confirmed that generalization is not concerned with total information but with the second order information.
dc.description.sponsorship成功大學,台南市
dc.format.extent7p.
dc.format.extent450448 bytes
dc.format.mimetypeapplication/pdf
dc.language.isozh_TW
dc.relation.ispartofseries1998 ICS會議
dc.subject.otherNeural Networks
dc.titleSimple Structural Information to Optimize Neural Network Architectures
分類:1998年 ICS 國際計算機會議

文件中的檔案:
檔案 描述 大小格式 
ce07ics001998000214.pdf439.89 kBAdobe PDF檢視/開啟


在 DSpace 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。