教學大綱表 (109學年度 第1學期)
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
Course Title		 (中文) 圖形識別
(英文) Pattern Recognition 		開課單位
Departments		 資訊工程研究所
課程代碼
Course No.		 I4560
授課教師
Instructor		 虞台文
學分數
Credit		 3.0 必/選修
core required/optional		 選修 開課年級
Level		 研究所
先修科目或先備能力(Course Pre-requisites)：Linear Algebra, Probability
課程概述與目標(Course Overview and Goals)： 圖形識別為智慧型系統重要的一個單元，為各種辨識技術，如：電腦視覺、語音辨識、生物辨識等，的主要基礎。主要授課內容包括：各種識別技術、特徵擷取方法、與機器學習等。本課程對未來從事各項智慧型系統的深入研究，有莫大幫助。
教科書(Textbook) Pattern Classification (2nd Edition)
Richard O. Duda, Peter E. Hart, and David G. Stork
參考教材(Reference) Computer Manual in MATLAB to Accompany Pattern Classification, Second Edition, by David G. Stork, Elad Yom-Tov
課程大綱 Syllabus 學生學習目標
Learning Objectives		 單元學習活動
Learning Activities		 學習成效評量
Evaluation		 備註
Notes
序
No.		 單元主題
Unit topic		 內容綱要
Content summary
1 Introduction 1. The goal of pattern classification
2. The main components
3. Some practical examples 		Introduction  
2 Bayesian Decision Theory 1. Bayesian Decision Theory
2. Classifiers, Discriminant Functions, and Decision Surfaces 		Bayesian Decision Theory  
3 Bayesian Decision Theory 3. The Normal Density
4. Discriminant Functions for the Normal Density 		Bayesian Decision Theory  
4 Maximum Likelihood 1. Maximum Likelihood Estimation
2. Baysian Estimation 		Maximum Likelihood  
5 Bayesian Parameter Estimation 1. Bayesian Parameter Estimation: Gaussian Case
2. Bayesian Parameter Estimation: General Theory 		Bayesian Parameter Estimation  
6 Hidden Markov Models 1. Hidden Markov Models
2. Evaluation, Decoding, and Learning 		Hidden Markov Models  
7 Nonparametric Techiques 1. Density Estimation
2. Parzen window
3. Nearest-Neighbor Estimation 		Nonparametric Techiques  
8 Nonparametric Techiques 4. Nearest-Neighbor Rule
5. Metrics and Nearest-Neighbor Classification 		Nonparametric Techiques  
9 Review Review Mid-term  
10 Linear Discriminant Functions 1. Linear Discriminant Functions and Decision Surfaces
2. Two-Category Linearly Separable Case
3. Minimizing the Perceptron Criterion Function 		Linear Discriminant Functions  
11 Linear Discriminant Functions 4. Relaxation Procedures
5. Minimum Squared-Error Procedures 		Linear Discriminant Functions  
12 Multilayer Neural Networks 1. Feedforward Operation and Classificaion
2. Backpropagation Algorithm
3. Error Surface 		Multilayer Neural Networks  
13 Multilayer Neural Networks 4. Backpropagation as Feature Mapping
5. Backpropagation, Bayes Theory and Probability
6. Practical Techniques for Improving Backpropagaion 		Multilayer Neural Networks  
14 Stochastic Methods 1. Stochastic Search
2. Boltzmann Learning 		Stochastic Methods  
15 Nonmetric Methods 1. Decision Trees
2. CART 		Nonmetric Methods  
16 Nonmetric Methods 3. Grammatical Methods
4. Grammatical Inference 		Nonmetric Methods  
17 Unsupervised Learning and Clustering 1. Unsupervised Bayesian Learning
2. Data Description and Clustering 		Unsupervised Learning and Clustering  
18 Review Review Final  


教學要點概述：
1.自編教材 Handout by Instructor：
□ 1-1.簡報 Slids
□ 1-2.影音教材 Videos
□ 1-3.教具 Teaching Aids
□ 1-4.教科書 Textbook
□ 1-5.其他 Other
□ 2.自編評量工具/量表 Educational Assessment
□ 3.教科書作者提供 Textbook

成績考核 Performance Evaluation：

教學資源(Teaching Resources)：
□ 教材電子檔(Soft Copy of the Handout or the Textbook)
□ 課程網站(Website)
扣考規定：http://eboard.ttu.edu.tw/ttuwebpost/showcontent-news.php?id=504