ARIN Courses

This course covers advanced Python programming skills for artificial intelligence (AI) applications. Students will learn to use popular AI libraries such as NumPy, Matplotlib, and Pandas, as well as deep learning frameworks like TensorFlow and PyTorch. Topics covered include data manipulation, visualization, and building neural networks. Prior experience in object-oriented programming is required.

This course provides a comprehensive coverage of the theoretical and practical foundations of artificial intelligence. Students will learn the basic concepts and techniques of the core AI subareas, including search, logic, knowledge representation, machine learning, natural language processing, computer vision, robotics, sequential decision making, and probabilistic reasoning. This course is designed to prepare students for more specialized AI courses.

This course provides a comprehensive coverage of both conventional and modern machine learning models and algorithms. Students will learn the theoretical foundations of machine learning and gain hands-on experience through software project experience. Topics covered include supervised and unsupervised learning for solving a wide range of machine learning tasks. Students will also learn how to evaluate and select machine learning models and apply these techniques to real-world problems.

This course explores ethical considerations in the design, development, and deployment of artificial intelligence (AI) systems. Students will examine the social impacts of AI and the ethical challenges that arise in areas such as privacy, bias, transparency, and accountability. Through case studies and discussions, students will develop a framework for ethical decision-making in the development and deployment of AI systems.

This course provides an in-depth understanding of machine learning techniques for computer vision and their applications in the field of artificial intelligence. Students will learn how to build and train different machine learning models for a wide range of computer vision tasks, including segmentation, recognition, and generation of visual data. Prior knowledge of Python programming and machine learning is required.

This course provides an in-depth understanding of machine learning techniques for natural language processing and their applications in the field of artificial intelligence. Students will learn how to build and train different machine learning models for different natural language processing tasks, such as sentiment analysis, text classification, and language translation. Prior knowledge of Python programming and machine learning is required.

This course aims to help students explore the rapidly growing technologies underlying foundation models and general artificial intelligence. Not only will students learn the fundamental concepts and techniques used for training foundation models, they will also learn how to make effective use of them through prompting and integration into other artificial intelligence systems. Prior knowledge of Python programming and machine learning is required.

This course provides an in-depth exploration of advanced AI techniques, including Markov decision processes, Q-learning, policy gradient methods, and deep reinforcement learning. Students will learn how to apply these techniques to real-world applications, such as robotics, game playing, and autonomous systems. Through hands-on projects and assignments, students will develop specialized skills useful for developing intelligent systems. Prior knowledge of Python programming and machine learning is required.

Human-computer interaction (HCI) is an interesting and important area of study, providing the human perspective to computing. This course emphasizes on techniques, models, theories, and applications for designing, prototyping, and evaluating current and future interactive intelligent systems for human use. Besides technology and innovation, it also touches on issues like ethics and social responsibilities related to technologies, especially the emerging innovations of artificial intelligence, in the real world. Selected topics may include multimodal interaction design, ubiquitous/mobile computing, virtual/augmented reality, agents and robots, and HCI applications in various domains such as education, health, urban sustainability, and scientific discoveries.

This course will equip students with practical knowledge of medical imaging and analysis with deep learning techniques. It will cover fundamental knowledge of medical imaging and various medical image analysis tasks, including computer-aided detection, segmentation, diagnosis and prognosis. Deep learning methods for solving these tasks will be introduced and state-of-the-art methods will be discussed. The remaining significant challenges and limitations will also be presented, including limited amount of labeled data, deep learning with interpretation and generalization issues, etc.

This course aims to teach students using artificial intelligence (AI) to solve cybersecurity problems. Students will learn general principles in different cybersecurity domains, e.g., cybersecurity mindsets, cryptographic methods, software security, network security, and hardware security. Moreover, they will also learn how to effectively apply AI techniques to solve problems in cybersecurity domains and contexts.

With large-scale medical datasets being available, artificial intelligence, especially deep learning, has dramatically advanced the field of medicine and healthcare. Computer-aided analytical tools have been developed to assist doctors in disease diagnosis and prognosis. This course will introduce the fundamentals of deep learning methods, including discriminative and generative models, and apply these methods for analyzing a variety of medical data modalities, such as structural and functional medical imaging, genomics, electrical health records, etc. In addition, various applications covering cancer diagnosis and prognosis will be introduced. This course will equip students with practical knowledge of artificial intelligence for healthcare and medicine.

The course aims to introduce the concepts, methods, and applications of automated and AI techniques in software engineering problems. The course will cover topics such as software fault detection, code coverage, unit test generation, mutation analysis, search-based software engineering, fault localization, code repair, code generation, vulnerability analysis, large language models for code, performance and benchmarking of coding models, and empirical studies. The course will also explore the challenges, opportunities, tool support, and industry adoption of using AI in software engineering.

This course covers selected topics in artificial intelligence and its applications that reflect recent developments not covered by existing MSc(AI) courses. The course may be repeated for credit if different topics are covered.

This course aims to provide practicum training to MSc(AI) students through a capstone project on a specific topic of artificial intelligence (AI) relevant to MSc(AI). Students will learn and practise the project planning and reporting skills necessary for completing an individual or group project. Students will also learn to demonstrate professionalism and integrity in AI system development. Subject to approval, part of the project may be conducted in the form of internship. Nevertheless, project management and assessment will still be the responsibility of the University.