|
課程名稱 |
圖形分析辨認
Pattern Analysis and Classification |
|
開課學期 |
104-1 |
|
授課對象 |
電機資訊學院 資訊網路與多媒體研究所 |
|
授課教師 |
洪一平 |
|
課號 |
CSIE5079 |
|
課程識別碼 |
922 U3030 |
|
班次 |
|
|
學分 |
3 |
|
全/半年 |
半年 |
|
必/選修 |
選修 |
|
上課時間 |
星期五2,3,4(9:10~12:10) |
|
上課地點 |
資102 |
|
備註 |
總人數上限：100人 |
|
Ceiba 課程網頁 |
http://ceiba.ntu.edu.tw/1041CSIE5079_PR |
|
課程簡介影片 |
|
|
核心能力關聯 |
核心能力與課程規劃關聯圖 |
|
課程大綱
|
|
為確保您我的權利,請尊重智慧財產權及不得非法影印
|
|
課程概述 |
The outline of this course is given below.
I. Pattern Recognition Overview
II. Bayesian Decision Theory
III. Supervised Learning Using Parametric Approaches
IV. Supervised Learning Using Non-parametric Approaches
V. Linear Discriminant Functions
VI. Unsupervised Learning and Clustering
VII. Special Topics in PR |
|
課程目標 |
The goal of this course is to introduce the basic concepts and techniques used
in the field of pattern recognition (PR). Broadly speaking, PR is a science
that concerns the classification (or recognition) of measurements. It has many
important applications, for example, document analysis, face recognition,
fingerprint identification, speech recognition, medical diagnosis, data
mining, and information retrieval. |
|
課程要求 |
|
|
預期每週課後學習時數 |
|
|
Office Hours |
每週四 15:00~16:00 備註： 助教時間 |
|
指定閱讀 |
R. Duda, P. Hart, D. Stork, Pattern Classification, 2nd Ed., John Wiley and Sons, 2000.
|
|
參考書目 |
1. S. Theodoridis, K. Koutroumbas, Pattern Recognition, 4th ed., Academic
Press, 2009.
2. C. M. Bishop, Pattern Recognition and Machine Learning, Springer, 2006.
|
|
評量方式
(僅供參考) |
|
No. |
項目 |
百分比 |
說明 |
|
1. |
Term Project and Presentation |
45% |
|
2. |
Mid-Term Exam |
30% |
|
3. |
Homework assignments |
20% |
|
4. |
Class Participation |
5% |
|
|
|
週次 |
日期 |
單元主題 |
|
第1週 |
09/18 |
Introduction |
|
第2週 |
09/25 |
Chapter 1. Pattern Recognition Overview |
|
第3週 |
10/02 |
Chapter 2. Bayesian Decision Theory |
|
第4週 |
10/09 |
國慶補假 |
|
第5週 |
10/16 |
Chapter 2. Bayesian Decision Theory |
|
第6週 |
10/23 |
Chapter 2. Bayesian Decision Theory |
|
第7週 |
10/30 |
Chapter 2. Bayesian Decision Theory
Chapter 3. Supervised Learning Using Parametric Approaches |
|
第8週 |
11/06 |
Chapter 3. Supervised Learning Using Parametric Approaches |
|
第9週 |
11/13 |
Chapter 3. Supervised Learning Using Parametric Approaches |
|
第10週 |
11/20 |
Closed-Book Exam |
|
第11週 |
11/27 |
Chapter 4 Supervised Learning Using Nonparametric Approaches |
|
第12週 |
12/04 |
Chapter 4. Supervised Learning Using Nonparametric Approaches
Chapter 5. Linear Discriminant Functions |
|
第13週 |
12/11 |
Oral Proposal (5~8 minutes)
Chapter 5. Linear Discriminant Functions |
|
第14週 |
12/18 |
1. Term Project: Evaluation for Competition
2. HCRFs for Human Action Recognition
3. Decision Trees (http://youtu.be/-dCtJjlEEgM) |
|
第15週 |
12/25 |
Chapter 10. Unsupervised Learning and Clustering
Special Topic: CNN for Dimension Reduction
|
|
第16週 |
01/01 |
元旦放假 |
|
第17週 |
01/08 |
1. Chapter 10. Unsupervised Learning and Clustering
2. Neural Network (https://www.youtube.com/watch?v=q0pm3BrIUFo)
3. Deep Learning (https://www.youtube.com/watch?v=n1ViNeWhC24) |
|
第18週 |
01/15 |
Term Project Final Presentation and Competition |
|