銘傳大學電腦與通訊工程學系課程大綱英文版

connectionviewΤεχνίτη Νοημοσύνη και Ρομποτική

17 Νοε 2013 (πριν από 3 χρόνια και 8 μήνες)

86 εμφανίσεις

Department of
Information
and Telecommunications
Engineering
,

Ming Chuan University

Course
Syllabus

Course
Name

Pattern Recognition

Course Number

05436

Grade / Semester

Grade four

Total C
redits

3

R
equired / Elective

Elective

Course

Weekly
H
ours

3

Prereq
uisite

Course

Calculus,
Linear Algebra, Probability and Statistics

Course

Description

T
he 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.

Learning

O
bjectives

After completing this course, the student will
be
able to:

1.

Understand what are the different steps that enable a Pattern Recognition
(PR) system to classify an input pattern.

2.

Familiarize with the PR terminology such as: segmentation, feature
ex
traction, classification, post processing, training,
supervised/unsupervised learning and reinforcement learning.

3.

Measure or compute the minimum error rate classification and decision
regions for classical density functions.

Learning

Outcome

Upon succes
sful completion of this course, the student will have
demonstrated the abilities to:

1.

Compute the Maximum Likelihood (ML) estimator of some density
functions, distinguish between ML and Bayes methods.

2.
Develop code in MATLAB for nonparametric techniques
such as the
k
-
Nearest Neighbor rule to classify patterns.

3.
Apply linear discriminant function as a model of classification.

4.
Cluster data using k
-
means algorithm.

5.
Understand the Back
-
propagation algorithm central to the Neural Network
approach.

Course

Outline

This course includes the following major topics:

1
. Pattern Recognition Overview

2
. Bayesian Decision Theory

3
. Supervised Learning Using Parametric Approaches

4
. PCA and LDA

5.

Supervised Learning Using Non
-
parametric Approaches

6
. Line
ar Discriminant Functions

7
. Unsupervised Learning and Clustering

8
. Other Related Topics

Note




The Relationship between Learning Objectives and Department Goal





偲数P牥⁨楧r
-
t散e⁰牯 敳獩潮慬猠睩瑨⁣牥慴楶攠瑨楮歩湧Ⱐ瑨攠n扩汩ty 潦⁡湡 ys楳Ⱐ扲
潡搠
睯牬摶楥w
:

佢樠ㄮO

T牡楮楮朠瑨攠獴畤敮瑳⁷楴栠瑥i洠獰楲楴⁡湤⁴桥⁡扩汩by

潦⁣牥慴楶攠瑨楮歩湧⁴桲n畧栠

瑨t

牥獥慲捨r灲潪散瑳

佢O


2

灲潧牡m 捥牴cf楥搠瑨牯畧栠瑨攠灲潦敳獩潮慬⁡捣牥e楴慴楯i





䙯捵猠潮⁴桥⁩湴 杲慴楯渠潦⁩湦潲o慴a潮o慮搠瑥汥捯浭畮m
捡c楯i⁴散桮潬潧y
:


佢樠
2


C
潵o獥猠摩癩摥搠楮瑯⁦潵爠瑲慣歳⁩湣汵摩湧⁴n汥捯浭畮楣慴楯渠瑥捨a潬潧yⰠ
湥瑷潲
k


捯浭畮楣u瑩潮Ⱐt浢敤摥搠dy獴s洠慮搠浵汴m浥摩愠捯浭畮楣慴楯m⁳y獴sm

佢樠
2
.
2

A
汬⁰牯l牡m⁴牡捫⁢潴栠捯癥牥搠瑨攠e湯睬敤n
攠潦⁣ m灵瑥爠捯浭畮楣u瑩潮

慮a

楮i潲o慴楯渠瑥捨湯n潧y





䥮瑥杲慴攠瑨攠a桥h牥瑩捡氠r潵湤慴楯湳⁡湤n灲慣瑩捡氠慰p汩捡瑩潮l
:

佢樠
3


C
潵牳敳⁣潶 牥搠瑨攠瑨敯r整楣慬⁡e搠灲慣瑩捡氠慲敡⁡湤⁴桥⁦畴畲攠瑲敮摳

佢樠
3
.
2

䕳瑡扬楳栠瑨攠T敬散e浭畮楣慴楯渠
T
e捨湯汯cy
L
慢Ⱐ乥a睯w欠
C
o浭u湩捡瑩
潮o
L
慢Ⱐam扥b摥搠
S
ys瑥m
L
慢⁡湤a䵵汴M浥摩愠
C
o浭畮u捡瑩潮c
S
ys瑥m
L
慢⁡湤a
汥慲渠瑨l⁰牡 瑩捡氠楳t略猠瑨牯畧栠s桥⁥硰敲ime湴n





The Relationship between Learning Objectives and Learning Outcomes





A
扩汩ty⁴漠慰灬y湯睬敤来n m慴桥浡瑩捳Ⱐ獣楥湣攬⁡湤n
敮杩湥敲楮e





A
扩汩ty⁴漠潲条湩g攬⁡湡ey穥⁡z搠灲潣敳猠灲潢汥ms





A
扩汩ty⁴漠摥獩杮s慮搠數散畴攠灲潪散瑳





A
扩汩ty⁴漠摥獩杮s愠ay獴sm⁡ 搠捯mp潮o湴
s





A
扩汩ty⁴漠 畮捴楯渠潮nm畬瑩
-
摩獣楰d楮慲y 瑥tms





A
扩汩ty⁴漠楮瑥杲慴攠捯m灵瑥爠p湦潲
m慴楯i⁡湤⁴敬散 浭畮楣慴楯渠瑥捨湯汯ny






A
扩汩ty⁴漠捯浭m湩捡瑥⁥nf散瑩癥eyⰠ慮, 睯牫⁴潧整桥爠瑯⁣h潰o牡瑥⁡猠愠瑥rm



C8

K
湯睬敤来w⁣ 湴nm灯牡py 楳獵敳⁡n
搠瑨攠tm灡捴p潦⁩湦潲o慴a潮⁡湤

瑥汥to浭畮楣慴楯湳i
敮杩湥敲楮朠楮⁳潣ie瑡氠捯湴數c





R
e
捯杮楴楯渠潦⁴桥敥搠 潲Ⱐ慮搠慮⁡扩汩,y t漠敮条来o楮楦e
-
汯湧敡牮楮



䌱C

U
n摥牳瑡湤d湧f⁰牯 敳獩潮慬⁡湤⁥瑨楣慬⁲敳灯湳a扩汩by