教學大綱表
請遵守智慧財產權,勿使用非法影印教科書,避免觸法。
課程名稱 (中文) 類神經系統及實驗
(英文) Artificial Neural Systems And Laboratory
開課單位 電機工程研究所
課程代碼 E5770B
授課教師 許超雲
學分數 3.0 必/選修 選修 開課年級 研究所
先修科目或先備能力:
課程概述與目標: 建立基本機器 學習之基礎及未來研究之能力
教科書
參考教材
課程大綱 學生學習目標 單元學習活動 學習成效評量 備註
單元主題 內容綱要
1 類神經系統發展史 類神經系統定義及相關研究 了解類神經系統定義
  • 講授
  • 閱讀討論
  •  
    2 Perceptron Percetron learning algorithm
  • 心得發表
  • 講授
  • 實驗
  •  
    3 Adline/madline Widrow learning LMS learning
  • 實作
  • 講授
  •  
    4 introduction to backprogation BP Architecture and learning Rule Architcture and learning rule
  • 講授
  • 實驗
  •  
    5 concave and convex for machine learning concave and convex for machine learning The complexity of learning
  • 講授
  •  
    6 Discusion of Project 1 and 2 discusion of project 1: random number generator

    Project 2: Percetron Learning
    Coding Algorithm
  • 個案研究
  • 心得發表
  • 講授
  • 實驗
  •  
    7 Improve the BP Improve learnig algorithm and Architecture of BP Improve learnig algorithm and Architecture of BP  
    8 Radical Basis Fuction Network Architecture of RBF and Learning Rule Architecture of RBF and Learning Rule
  • 講授
  •  
    9 Midterm Midterm Midterm
  • 講授
  • 期中考
  •  
    10 Self-organizing Feature map Architecture and learning Rule for SOFM Architecture and learning Rule for SOFM
  • 講授
  •  
    11 Gradient and discrete Hofield Model The architecture and Learning rule of Hopfield model The architecture and Learning rule of Hopfield model
  • 講授
  • 實驗
  •  
    12 Boltzman Machine Architecture and learning rule of BM Architecture and learning rule of BM
  • 講授
  •  
    13 Support vector machine (I) Margin/support vector 1) Margin/support vector
  • 講授
  •  
    14 Support Vector machine (2) SVM architecture and learning rule SVM architecture and learning rule  
    15 reinforcement learning reinforcement learning basic theorem and applications
  • 講授
  •  
    16 Adaptive resonant T(ART) Plasticity and stabaility ART 1
  • 期末考
  •  
    17 Final exam final exam final exam
  • 期末考
  •  

    教學要點概述:
    教材編選: ■ 自編教材 □ 教科書作者提供
    評量方法: 期末考:30%   期中考:30%   實驗:40%  
    教學資源: ■ 教材電子檔 □ 課程網站
    扣考規定:http://eboard.ttu.edu.tw/ttuwebpost/showcontent-news.php?id=504