一、課程說明(Course Description)

This course introduces intelligent problem solving methods, knowledge

representaiton, machine learning theories and methods, intelligent systems

applications, the content includes:

1. heuristic search, (hill climbing, A*)

2. planning and problem solving, (partial order planning)

3. logic theorem proving and automated reasoning,

4. knowledge representation and expert systems,

5. uncertain reasoning, (Bayesian belief networks, Kaman filtering, MCMC algorithm)

6. machine learning & deep learning (decision tree, reinforcement learning, CNN, RNN, GAN)

7. natural language processing, (parsing, semantic embedding)

8. computer vision, (neural network vision)

9. intelligent agents. (coordination and negotiation)





二、指定用書(Text Books)



Stuart Russel and Peter Norvig, Artificial Intelligence: A Modern Approach,

Pearson education, Inc. 3nd Edition, 2010.

Deep Learning with Python, Francois Chollet,



三、參考書籍(References)



Patrick Henry Winston, Artificial Intelligence, 3rd edition.





四、教學方式(Teaching Method)



lectures,

homework exercises,

term programming project,

Quiz exams





五、教學進度(Syllabus)





1. Introduction and intelligent agents (1 weeks)

2. Problem solving (heuristic search and Constraint Satisfaction problems) (2 weeks)

hill climbing; simulated annealing, A* algorithms,

3. Machine Learning (5 weeks) decision tree, error back propagation, Q-learning, conceptual

clustering, deep learning CNN, RNN, LSTM, GAN

(mid term project due)

4. Uncertainty and probabilistic reasoning [Bayesian networks, MCMC] (1 weeks)

5. Knowledge and logical reasoning (1 week) non-monotonic reasoning,

6. Agent Planning (1 weeks) partial order planning

7 . Natural language processing (1 week)

(Final exam week; term project due)



六、成績考核(Evaluation)



Homework exercises 40%

Mid term project 20%

Final term project 30%

Participation 10%







七、可連結之網頁位址