RIKOS, APOSTOLOS - HKUST Class Schedule & Quota

COURSE INFO

DESCRIPTION	This course provides guidance to undergraduate students of the AI major for their academic path and future. This course is mostly introductory and aims to inspire UG students for their academic path development and growth of maturity during their UG study. Activities may include seminars, workshops, advising and sharing sessions, interaction with faculty and teaching staff, and discussion with student peers or alumni. Graded P or F.

DESCRIPTION

This course provides guidance to undergraduate students of the AI major for their academic path and future. This course is mostly introductory and aims to inspire UG students for their academic path development and growth of maturity during their UG study. Activities may include seminars, workshops, advising and sharing sessions, interaction with faculty and teaching staff, and discussion with student peers or alumni. Graded P or F.

AIAA 1010 - Academic Orientation for AI Students (1 unit)

Section	Date & Time	Room	Instructor	Quota	Enrol	Avail	Wait	Remarks
L01 (6417)	Mo 04:30PM - 05:20PM	Rm 101, W1	BAI, Ge CHEN, Huangxun CHU, Xiaowen KAN, Ge Lin LIANG, Junwei QIN, Chengwei RIKOS, APOSTOLOS WANG, Xin WANG, Zeyu XIE, Sihong XIE, Zeke YANG, Menglin YUE, Yutao	100	55	45	0	The class will be delivered by the following instructors and contents as below: W1: Zeke XIE - Overview of Deep Learning Theory W2: Yutao YUE - Towards Conscious AI W3: Menglin YANG - Foundation of LLM: From Pretraining, Mid Training to Post Training W4: Xiaowen CHU - Magic of Low-Precision Computing behind LLMs W5: Sihong XIE - Interpretable AI W6: Xin WANG - Foundations of Quantum Computing W7: Ge BAI - Quantum Entanglement and Applications W8: Chengwei Qin - LLM Reasoning and Agent W9: Zeyu WANG - Toward Synergistic Human-AI Content Creation W10: Huangxun CHEN - Overview of Embedded AI W11: Ge Lin Kan - Generative AI for Urban Digital Twin W12: Junwei Liang - Towards General Service Embodied AI W13: Apostolos RIKOS - AI and Multi-Agent Networks

COURSE INFO

PRE-REQUISITE	UFUG 1103 OR UFUG 1106
DESCRIPTION	This course aims to teach students the basic math concepts for Artificial Intelligence (AI). Key topics include fundamental Linear Algebra (Matrix Calculations, Norms, Eigenvectors and Eigenvalues), Calculus (Derivative, Taylor series, Multivariate Calculus), and Probability Theory (Distributions, Statistics of Random Variables, Bayes’ theorem). With these mathematical concepts, some basic principles of numerical optimization and typical AI algorithms (Gradient Descent, Maximum-likelihood, Regression, Least Square Estimation, Spectral Clustering, Matrix Decomposition, etc.) will also be introduced as examples to better relate math to AI. The approach of this course is specifically AI application oriented, aiming to help students to quickly establish a fundamental mathematical knowledge structure for AI studies. Through this course, students will acquire the fundamental mathematical concepts required for AI, understand the connections between AI and mathematics, and get prepared to learn the mathematical principles, formulas, inductions, and relevant proofs for advanced AI algorithms.

PRE-REQUISITE

UFUG 1103 OR UFUG 1106

DESCRIPTION

This course aims to teach students the basic math concepts for Artificial Intelligence (AI). Key topics include fundamental Linear Algebra (Matrix Calculations, Norms, Eigenvectors and Eigenvalues), Calculus (Derivative, Taylor series, Multivariate Calculus), and Probability Theory (Distributions, Statistics of Random Variables, Bayes’ theorem). With these mathematical concepts, some basic principles of numerical optimization and typical AI algorithms (Gradient Descent, Maximum-likelihood, Regression, Least Square Estimation, Spectral Clustering, Matrix Decomposition, etc.) will also be introduced as examples to better relate math to AI. The approach of this course is specifically AI application oriented, aiming to help students to quickly establish a fundamental mathematical knowledge structure for AI studies. Through this course, students will acquire the fundamental mathematical concepts required for AI, understand the connections between AI and mathematics, and get prepared to learn the mathematical principles, formulas, inductions, and relevant proofs for advanced AI algorithms.

AIAA 2711 - Mathematics for AI (3 units)

Section	Date & Time	Room	Instructor	Quota	Enrol	Avail	Wait	Remarks
L02 (6419)	Mo 09:00AM - 11:50AM	Lecture Hall C	RIKOS, APOSTOLOS	90 Quota/Enrol/Avail Year 2 UG students: 85/58/27 Year 3 UG Students: 5/1/4	59	31	0

COURSE INFO

PRE-REQUISITE	UFUG 2104 AND (UFUG 2601 OR UFUG 2602)
DESCRIPTION	The implementation of autonomous systems requires agents to learn how to make decisions. Reinforcement learning is a powerful paradigm for achieving such a goal, and it is relevant to an enormous range of tasks, including robotics, game playing, operations research, healthcare and more. This course provides a solid introduction to the field of reinforcement learning. Students learn about the core challenges and approaches, including generalization and exploration. Through the combination of lectures, written and coding assignments, and course projects, students are equipped with modeling and learning algorithm techniques for sequential decision-making problems. Assignments include the basics of reinforcement learning as well as deep reinforcement learning — an extremely promising new area that combines deep learning advancements with reinforcement learning.

PRE-REQUISITE

UFUG 2104 AND (UFUG 2601 OR UFUG 2602)

DESCRIPTION

The implementation of autonomous systems requires agents to learn how to make decisions. Reinforcement learning is a powerful paradigm for achieving such a goal, and it is relevant to an enormous range of tasks, including robotics, game playing, operations research, healthcare and more. This course provides a solid introduction to the field of reinforcement learning. Students learn about the core challenges and approaches, including generalization and exploration. Through the combination of lectures, written and coding assignments, and course projects, students are equipped with modeling and learning algorithm techniques for sequential decision-making problems. Assignments include the basics of reinforcement learning as well as deep reinforcement learning — an extremely promising new area that combines deep learning advancements with reinforcement learning.

AIAA 3053 - Reinforcement Learning: Principles and Methods (3 units)

Section	Date & Time	Room	Instructor	Quota	Enrol	Avail	Wait	Remarks
L01 (6420)	Fr 12:00PM - 02:50PM	Rm 101, E1	RIKOS, APOSTOLOS	80	76	4	0