MIT OpenCourseWare


» 進階搜尋
 課程首頁
 教學大綱
 教學時程
 課堂講稿
 作業
 研習資料

教學大綱


本頁翻譯進度

燈號說明

審定:無
翻譯:羅嘉林(簡介並寄信)
編輯:朱學(簡介並寄信)

課程描述

對於物體辨識在實驗、神經學、計算、與應用等領域的關鍵議題與發現,提供全面性的介紹 。著重於物體的呈現方式,檢視3度空間物體如何有效率地對應解碼成可供辨識的2度空間影像。課程後半部的重心放在臉孔辨識 – 這是演化學上關於一般物體辨識的重要例證。描述關於人類臉孔辨識反應的實驗研究與近來在人工計算系統上對此能力的模擬。學生必須額外進行專題以取得研究所學分。



課程規定

10%: 上課
15%: 主持課堂討論並且做紀錄
10%: 在每堂課結束後,針對此堂課提出三個問題

  1. 開放性的研究問題 / 研究計畫想法
  2. 可以簡單回答的問題
  3. 複選題

25%: 期中考
40%: 學期專題




Description

Provides a comprehensive introduction to key issues and findings in object recognition in experimental, neural, computational, and applied domains. Emphasizes the problem of representation, exploring the issue of how 3-D objects should be encoded so as to efficiently recognize them from 2-D images. Second half focuses on face recognition, an ecologically important instance of the general object recognition problem. Describes experimental studies of human face recognition performance and recent attempts to mimic this ability in artificial computational systems. An additional project is required for graduate credit.



Requirements

10%: Class participation
15%: Lead a class discussion and scribe notes for one lecture
10%: Send three questions to scribe after each lecture

  1. Open research question / project idea
  2. A short answer question
  3. A multiple choice question

25%: Mid-term exam
40%: Term project




 
MIT Home
Massachusetts Institute of TechnologyTerms of UsePrivacy