This course gives the fundamentals for understanding artificial intelligence systems and their components. First, the students learn how to formulate problems and how to search for their solution. Then they learn how to explicitly represent knowledge and how to do inference based on it. Further, they learn planning for efficient inference. Finally, they learn machine learning in which machine automatically acquire knowledge.
By the end of this course, students will be able to:
1) Understand the necessity of artificial intelligence systems which support human intellectual activities in the information society.
2) Aquire elemental techniques used for building artificial intelligence systems.
3) Represent the process of human's intellectual production.
4) Do inferences based on the representation.
State space representation, Graph search, Heuristic search, A* search, Game, Minimax method, α-β pruning, Semantic network, Frame, Production system, Resolution principle, Forward inference, Backward inference, Default logic, Probabilistic inference, Bayesian network, GPS, Hierarchical planning, Partial order planning, Reactive planning, Linear classifier, Neural network, Decision tree
|✔ Specialist skills||Intercultural skills||Communication skills||Critical thinking skills||✔ Practical and/or problem-solving skills|
1) At the beginning of each class, the contents of the previous class are reviewed.
2) At the end of each class, an assignment is given, which should be submitted in the next class.
3) Attendance is taken in every class.
4) Students are recommended to learn the topics by themselves before coming to class.
|Course schedule||Required learning|
|Class 1||Introduction||Explain in the class.|
|Class 2||Search 1: State space representation, Graph search||Explain in the class.|
|Class 3||Search 2: Heuristic search, A* search||Explain in the class.|
|Class 4||Search 3: Game (Minimax method, α-β pruning)||Explain in the class.|
|Class 5||Knowledge representation 1: Semantic network, Frame||Explain in the class.|
|Class 6||Knowledge representation 2: Production system||Explain in the class.|
|Class 7||Inference 1: Resolution principle||Explain in the class.|
|Class 8||Inference 2: Forward and backward inference, Default logic||Explain in the class.|
|Class 9||Inference 3: Probabilistic inference (Bayesian network)||Explain in the class.|
|Class 10||Planning 1: GPS, Hierarchical planning||Explain in the class.|
|Class 11||Planning 2: Partial order planning, Reactive planning||Explain in the class.|
|Class 12||Machine learning 1: Linear classifier||Explain in the class.|
|Class 13||Machine learning 2: Neural network||Explain in the class.|
|Class 14||Machine learning 3: Decision tree, misc||Explain in the class.|
To enhance effective learning, students are encouraged to spend approximately 100 minutes preparing for class and another 100 minutes reviewing class content afterwards (including assignments) for each class.
They should do so by referring to textbooks and other course material.
Russel and Norvig, "Artificial Intelligence: A Modern Approach (3rd Edition)", Pearson
Students course scores are based on an assignment in every class (20% in total) and final exam (80%).
Students are expected to have taken "CSC.T242 ： Probability Theory and Statistics".