情報科学研究科Graduate School of Computer and Information Sciences
COT500K1(計算基盤 / Computing technologies 500)Global CIS Special Lecture 3 Global CIS Special Lecture 3
グローバルCIS特別講義3
内田 薫Kaoru UCHIDA
授業コードなどClass code etc
学部・研究科Faculty/Graduate school | 情報科学研究科Graduate School of Computer and Information Sciences |
添付ファイル名Attached documents | |
年度Year | 2022 |
授業コードClass code | TZ028 |
旧授業コードPrevious Class code | |
旧科目名Previous Class title | |
開講時期Term | 春学期授業/Spring |
曜日・時限Day/Period | 火4/Tue.4 |
科目種別Class Type | |
キャンパスCampus | 小金井 |
教室名称Classroom name | 各学部・研究科等の時間割等で確認 |
配当年次Grade | |
単位数Credit(s) | 2 |
備考(履修条件等)Notes | |
実務経験のある教員による授業科目Class taught by instructors with practical experience | |
カテゴリーCategory |
すべて開くShow all
すべて閉じるHide All
授業の概要と目的(何を学ぶか)Outline and objectives
Pattern recognition and machine intelligence:
This course, conducted in English, is designed to give graduate students the fundamental knowledge of pattern recognition and machine intelligence
到達目標Goal
The goal of this course is to provide students with knowledge and understanding of fundamental pattern recognition and machine intelligence techniques and how to apply them to real world problems.
この授業を履修することで学部等のディプロマポリシーに示されたどの能力を習得することができるか(該当授業科目と学位授与方針に明示された学習成果との関連)Which item of the diploma policy will be obtained by taking this class?
Among diploma policies, "DP1" and "DP2" are related.
授業で使用する言語Default language used in class
英語 / English
授業の進め方と方法Method(s)(学期の途中で変更になる場合には、別途提示します。 /If the Method(s) is changed, we will announce the details of any changes. )
This course, conducted in English, will enable students to understand the basic approaches to pattern recognition and machine intelligence problems, which students should learn as an introduction to real world problems. Students will enjoy related practical Python programming using code samples provided by the instructor.
The course will mainly consist of lectures but time will be given for students to work on research and programming projects. Students are required to work on weekly programming exercises of CIS programming, such as mathematics and machine intelligence. Project/assignment outputs will be reviewed in the classroom.
アクティブラーニング(グループディスカッション、ディベート等)の実施Active learning in class (Group discussion, Debate.etc.)
あり / Yes
フィールドワーク(学外での実習等)の実施Fieldwork in class
なし / No
授業計画Schedule
授業形態/methods of teaching:対面/face to face
※各回の授業形態は予定です。教員の指示に従ってください。
1[対面/face to face]:Introduction
Introduction to pattern recognition and machine intelligence
2[対面/face to face]:Statistical Pattern Recognition 1
- Features and Their Distributions
- Feature Vectors and Feature Space
3[対面/face to face]:Statistical Pattern Recognition 2
- Likelihood and the Bayes' Law
- Feature Space, Principal Component Analysis and Eigenspace
4[対面/face to face]:Statistical Pattern Recognition 3
Economic gain and ROC curve
5[対面/face to face]:Statistical Pattern Recognition 4
Clustering and thresholding
6[対面/face to face]:Structural Pattern Recognition 1
Pattern Recognition by Syntax Analysis
7[対面/face to face]:Structural Pattern Recognition 2
Formal grammar and parsing
8[対面/face to face]:Midterm project
Midterm project workshop
9[対面/face to face]:Image features for matching
- Corner-based techniques
- Scale-invariant techniques
10[対面/face to face]:Image Matching 1
- Semantic Graph Matching
- Uninformed search for graph matching
11[対面/face to face]:Image Matching 2
- Heuristic search for graph matching
- Robust matching methods
12[対面/face to face]:3D image analysis 1
3D block world recognition
13[対面/face to face]:3D image analysis 2
3D shape from X
14[対面/face to face]:Final project
Final project workshop
授業時間外の学習(準備学習・復習・宿題等)Work to be done outside of class (preparation, etc.)
Reading, research and programming assignments.
Standard study time outside of class for preparation and review: 4 hours.
テキスト(教科書)Textbooks
Course materials will be provided in class.
参考書References
Richard O. Duda, Peter E. Hart, and David G.Stork, "Pattern Classification, second edition,” Wiley-Interscience, 2001.
C. M. Bishop, "Pattern Recognition and Machine Learning," Information Science and Statistics, Springer (October 1, 2007).
Willi Richert and Luis Pedro Coelho, "Building Machine Learning Systems With Python," Packt Publishing, 2013.
成績評価の方法と基準Grading criteria
Students will be evaluated on the basis of contribution in class (20%), and assignment outputs (80%).
学生の意見等からの気づきChanges following student comments
(None in particular.
Feedback from students will be encouraged throughout the course.)
学生が準備すべき機器他Equipment student needs to prepare
Students are expected to bring and use their laptop PCs for in-class programming exercises and presentations.