文化大學機構典藏 CCUR:Item 987654321/18020
English  |  正體中文  |  简体中文  |  全文笔数/总笔数 : 46962/50828 (92%)
造访人次 : 12353370      在线人数 : 850
RC Version 6.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
搜寻范围 查询小技巧:
  • 您可在西文检索词汇前后加上"双引号",以获取较精准的检索结果
  • 若欲以作者姓名搜寻,建议至进阶搜寻限定作者字段,可获得较完整数据
  • 进阶搜寻
    主页登入上传说明关于CCUR管理 到手机版


    jsp.display-item.identifier=請使用永久網址來引用或連結此文件: https://irlib.pccu.edu.tw/handle/987654321/18020


    题名: 應用類神經網路學習建築平面推論之研究
    作者: 溫國忠
    贡献者: 建築系
    关键词: 建築設計
    電腦輔助設計
    類神經網路
    案例學習
    日期: 2000-12
    上传时间: 2010-12-09 11:04:48 (UTC+8)
    摘要: 在實際的設計過程中,設計者常以案例的學習來獲得設計的知識,藉著案例所累積的經驗,從而對相關的設計問題提出全部份部份的解決方案。這樣的能力被認為是在過去案例的經驗中,所學習到的一種設計知識。而類神經網路是模仿生物的神經系統及學習認知行為所發展出來的模型,可以根據過去的案例經驗學習來解決問題,系統經由案例的學習,直接自動地擷取出新的知識,存於網路之中。本研究是應用類神經網路的技術建構案例學習的「類神經式自動設計系統」,再以台北地區公寓式住宅平面為例,以檢證此方法的有效性。其程序為先探討相關電腦輔助設計的理論系統與設計學習的發展,再探討類神經網路的理論方法,以作為本研究案例學習系統推導的核心,推導出類神經式自動設計的模型系統,來進行案例學習的操作,最後針對學的成果做檢覈。
    Existing method of design of computation utilize on a set of pre-decomposed design structures, and require knowledge engineers as human translators between designs and computer. To extend the problem solving abilities and to avoid the knowledge acquisition bottleneck of current design computation tools, systems allowing the problem-solver to learn form experience are necessary. Often designers are not aware subconscious levels. One possibility of knowledge acquisition is to learn form design examples by designers. The retrieved case my either match the current situation exactly or need modification. This leads to the fundamental assumptions of this thesis that applying case-based reasoning in a manageable structure, this research intends to use an artificial neural networks (ANN) approach to solve CBR problems in architectural layout design. The organization of this research is corresponding to the different steps of this research. First, the problem statement of this research is made and current developments of design computation are discussed. Secondly, a conceptual model of case-based reasoning in layout design using ANN is proposed. Thirdly, a computer system CBRANN is developed to demonstrate different approaches of proposed model. Finally, conclusions are made, and future extensions of this research are described. The results show that applying artificial neural networks on case-based reasoning in design is a feasible approach for building knowledge-based design systems in architecture.
    關聯: 建築與規劃學報 1卷3期 P.208-226
    显示于类别:[建築及都市設計學系所] 期刊論文

    文件中的档案:

    档案 描述 大小格式浏览次数
    index.html0KbHTML185检视/开启


    在CCUR中所有的数据项都受到原著作权保护.


    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - 回馈