Course Code: B62012H
Course Name: Artificial Intelligence: The Basics (B)
Credits: 3.0
Level: Undergraduate
Pre-requisite: Advanced Algebra, Calculus, Discrete Mathematics, Probability and Mathematical Statistics, Programming
Lecture Time: 15 weeks, 2 sessions/week, 2 hours/session
Course Description
This course is designed for undergraduate students with major in Computer Science. The purpose is to enable students to master basic theory, principle and realization of intelligent system in artificial intelligence. The course focuses on three main aspects: intelligent search, knowledge representation, and reasoning. Through the combination of teaching and programming, this course can develop students to use artificial intelligence technology to solve practical problems; students can also gradually gain experience in independent learning and researching.
Topics and Schedule
1.1. Definition of artificial intelligence
1.2. Primary school and development history
1.3. Main research field
1.4. Turing test
2.1. Search figure, blind searching, heuristic searching, evaluation function and A* algorithm (6 hrs)
2.2. And-or graph search problem, heuristic searching of and-or graph search problem, AO* researching, game tree searching, minimax game search process and a-b pruning method (6 hrs)
2.3. Advanced search, genetic algorithm, combined search (6 hrs)
3.1. Knowledge representation methods, production rule representation, semantic network representation, framework representation, resource description framework (8 hrs)
3.2. Logic reasoning methods, propositional logical, predicate logic expressions, predicate logic principle, Herbrand theorem (10 hrs)
3.3. Uncertainty reasoning, uncertainty measurement of rules and evidence, Bayesian inference (6 hrs)
3.4. Human brain and cognition, human brain structures and cognitive phenomenon, cognitive behavior of individuals and their social environment, calculation model of cognitive behavior (4 hrs)
4.1. Supervised learning, k-neighbors, decision tree, conditional information entropy criterion, Bayesian learning and graphical models (4 hrs)
4.2. Unsupervised learning, k-means clustering and clustering evaluation (2 hrs)
4.3. Neural network, neural network structure, BP algorithm and Hopfield network (2 hrs)
Grading
Textbook
[1] Ruling Lu. Artificial Intelligence. Science Press, Beijing, 1996.
[2] Zhongzhi Shi. Advanced Artificial Intelligence. Science Press, Beijing, 2011.
Reference