COMP7404D - Computational intelligence and machine learning

Summer Semester, 2022-23

Professor	W.Y. Chung
Teaching assistant	Yinqiang Zhang
Syllabus	This course will teach a broad set of principles and tools that will provide the mathematical, algorithmic and philosophical framework for tackling problems using Artificial Intelligence (AI) and Machine Learning (ML).  AI and ML are highly interdisciplinary fields with impact in different applications, such as, biology, robotics, language, economics, and computer science.  AI is the science and engineering of making intelligent machines, especially intelligent computer programs, while ML refers to the changes in systems that perform tasks associated with AI.  Ethical issues in advanced AI and how to prevent learning algorithms from acquiring morally undesirable biases will be covered. Topics may include a subset of the following: problem solving by search, heuristic (informed) search, constraint satisfaction, games, knowledge-based agents, supervised learning, unsupervised learning; learning theory, reinforcement learning and adaptive control and ethical challenges of AI and ML.
Introduction by Professor	This course will cover several topics in AI and ML.  We will start with traditional AI techniques including search, probability estimation, and Bayes rule.  We will then cover machine learning techniques, including unsupervised learning / reinforcement learning, and supervised learning.
Learning Outcomes	Course Learning Outcomes Relevant Programme Learning Outcomes CLO1. Understand the fundamental concepts of computational intelligence and machine learning PLO.5, 6, 7, 8, 9, 16 CLO2. Demonstrate awareness of the major challenges and risks facing computational intelligence and the complexity of typical problems within the field PLO.4, 6, 7, 8, 13, 14, 15 CLO3. Able to implement solutions to various problems in computational intelligence PLO.6, 7, 8, 9, 10, 11, 12 View Programme Learning Outcomes
Prior knowledge expected	Students who join this class are expected to have prior knowledge of data structures and algorithms, probability, linear algebra, and programming.
Compatibility	Nil
Topics covered	Course Content No. of Hours Course Learning Outcomes Introduction 2 CLO1, CLO2 Search, Probability Estimation, Bayes Rule 7 CLO1, CLO2, CLO3 Unsupervised Machine Learning / Reinforcement Learning 7 CLO1, CLO2, CLO3 Supervised Machine Learning 8 CLO1, CLO2, CLO3 Group Presentations 6 CLO3
Assessment	Description Type Weighting * Examination Period ^ Course Learning Outcomes Group Project Continuous Assessment 20% - CLO3 Quiz / Assignments Continuous Assessment 30% - CLO1, CLO2, CLO3 Final exam covering all taught content of the course Written Examination 50% 7 - 19 Aug 2023 CLO1, CLO2 * The weighting of coursework and examination marks is subject to approval ^ The exact examination date uses to be released when all enrolments are confirmed after add/drop period by the Examinations Office.  Students are obliged to follow the examination schedule.  Students should NOT enrol in the course if they are not certain that they will be in Hong Kong during the examination period.  Absent from examination may result in failure in the course. There is no supplementary examination for all MSc curriculums in the Faculty of Engineering.
Course materials	Recommended readings: Artificial Intelligence: A Modern Approach (4th Edition), Stuart Russell and Peter Norvig Reinforcement Learning: An Introduction, Richard S. Sutton and Andrew G. Barto Machine learning, by Tom Mitchell, McGraw Hill Machine learning: a probabilistic perspective, by Kevin Murphy, The MIT Press
Session dates	Date Time Venue Remark Session 1 13 Jun 2023 (Tue) 7:00pm - 10:00pm Online Zoom Session 2 17 Jun 2023 (Sat) 7:00pm - 10:00pm Online Zoom Session 3 20 Jun 2023 (Tue) 7:00pm - 10:00pm Online Zoom Session 4 24 Jun 2023 (Sat) 7:00pm - 10:00pm Online Zoom Session 5 27 Jun 2023 (Tue) 7:00pm - 10:00pm Online Zoom Session 6 4 Jul 2023 (Tue) 7:00pm - 10:00pm Online Zoom Session 7 8 Jul 2023 (Sat) 7:00pm - 10:00pm Online Zoom Session 8 11 Jul 2023 (Tue) 7:00pm - 10:00pm Online Zoom Session 9 15 Jul 2023 (Sat) 7:00pm - 10:00pm Online Zoom Session 10 18 Jul 2023 (Tue) 7:00pm - 10:00pm Online Zoom
Add/drop	12 June, 2023 - 17 June, 2023
Maximum class size	150
Moodle course website	HKU Moodle: https://moodle.hku.hk/course/view.php?id=102613 (Login using your HKU Portal UID and PIN) - Please note that the professor maintains and controls when to release the Moodle teaching website to students. - Enrolled students should visit the Moodle teaching website regularly for latest announcements, course materials, assignment submission, discussion forum, etc.