|
1.교수목표 및 강의개요 (Course Objectives &
Description)
1) 교수목표
This course provides a broad exposure to the advanced topics in artificial
intelligence. Main topics include knowledge representation, intelligent systems,
problem solving, planning, uncertainty, probabilistic reasoning, and other
topics. The current issues of AI will be also covered.
2) 강의개요
The objectives of this course are (1) to instruct algorithms and methods of
knowledge representation, knowledge learning and rule extraction for
developing an intelligent system, (2) to enable students to apply these
techniques in application which are related to their own interests, and (3)
to improve the students' ability to solve problems.
*
장애학생의 경우
장애학습지원센터와 강의 및 과제에 대한 사전 협의가 가능합니다.
2.주교재 (Required TextBook)
Artificial Intelligence: A Modern Approach (Third edition) by Stuart
Russell and Peter Norvig
3.평가방법 (Requirements & Grading)
- 중간고사 30%, 기말고사 40%, 프로그램 20%, 레포트 10%
* 장애학생의 경우 시험시간의 연장이 가능하며, 대필이나 컴퓨터를 활용하여
시험에 응할 수 있습니다.
4.주별
강의계획 (Schedule)
|
주 별
|
강의 및 실험실기내용
|
과제 및 기타 참고사항
|
|
제1주
|
Introduction of Artificial Intelligence
|
Writing Essay
|
|
제2주
|
Limitations of
Artificial Intelligence and Rule-based Methodology I
|
|
|
제3주
|
Rule-based Methodology II
|
Coding
|
|
제4주
|
Knowledge Representation by Logic
|
|
|
제5주
|
Knowledge Representation by Semantic Web and Others
|
|
|
제6주
|
Rule-based Classification
|
|
|
제7주
|
Machine Learning by C4.5
|
Coding
|
|
제8주
|
Mid term exam
|
|
|
제9주
|
Onthology I
|
|
|
제10주
|
Onthology II
|
Implementation of Onthology (Protege)
|
|
제11주
|
Machine Learning by CRFs, SVM
|
|
|
제12주
|
Machine Learning by HMM
|
|
|
제13주
|
Knowledge Extraction based on Statistical Methods
|
Word Extracting Experiment
|
|
제14주
|
Solving Real World Problems by AI Methods
|
Word Similarity Experiment
|
|
제15주
|
Information Retrieval and Data Mining
|
|
|
제16주
|
Final exam
|
|
5.참고문헌 (References)
- Protege 2000 - SVM, CRF 관련 자료 - Wikipedia - Foundation of
Statistical Natural Language Processing, C. Manning, H. Schutze, The MIT
Press, 2001
|