Description of the courses of the diploma in artificial intelligence technology
Description of the courses of the diploma in artificial intelligence technology
Compulsory Courses
CS501 Deep Learning [3 CH]
This course is an introduction to deep learning, a branch of machine learning concerned with the development and application of modern neural networks. Deep learning algorithms extract layered high-level representations of data in a way that maximizes performance on a given task. For example, asked to recognize faces, a deep neural network may learn to represent image pixels first with edges, followed by larger shapes, then parts of the face like eyes and ears, and, finally, individual face identities. Deep learning is behind many recent advances in AI, including Siri’s speech recognition, Facebook’s tag suggestions and self-driving cars. This course will cover a range of topics from basic neural networks, convolutional and recurrent network structures, deep unsupervised and reinforcement learning, and applications to problem domains like speech recognition and computer vision.
CS502 Reasoning and Agents [3 CH]
This course focuses on approaches relating to representation, reasoning and planning for solving real world inference. The course illustrates the importance of (i) using a smart representation of knowledge such that it is conducive to efficient reasoning, and (ii) the need for exploiting task constraints for intelligent search and planning. The notion of representing action, space and time is formalized in the context of agents capable of sensing the environment and taking actions that affect the current state. There is also a strong emphasis on the ability to deal with uncertain data in real world scenarios and hence, the planning and reasoning methods are extended to include inference in probabilistic domains.
CS503 Vision and Robotics [3 CH]
Robotics and Vision applies AI techniques to the problems of making devices capable of interacting with the physical world. This includes moving around in the world (mobile robotics), moving things in the world (manipulation robotics), acquiring information by direct sensing of the world (e.g. machine vision) and, importantly, closing the loop by using sensing to control movement. Applying AI in this context poses certain problems, and sets certain limitations, which have important effects on the general software and hardware architectures. For example, a robot with legs must be able to correct detected imbalances before it falls over, and a robot which has to look left and right before crossing the road must be able to identify approaching hazards before it gets run over. These constraints become much more serious if the robot is required to carry both its own power supply and its own brain along with it. This module introduces the basic concepts and methods in these areas, and serves as an introduction to the more advanced robotics and vision modules.
CS504 Internet of Things (IoT) [3 CH]
The course introduces advanced concepts and methodologies to design, build, and deploy IoT solutions, and discusses various technologies and protocols used for communication – including next-generation, IoT-friendly applications and physical-layer protocols. Participants will gain a thorough understanding of widely accepted IoT frameworks and standards. The course covers popular, service-rich cloud platforms and focuses on how to build and deploy IoT solutions. Practical use cases and case studies are included to ensure that the participant develops an ability to work through real-life scenarios
CS512 Artificial Intelligence Project [6 CH]
This course provides qualified students an opportunity to work with faculty members in research and development projects in areas of current interest in Artificial Intelligence. Students are expected to carry out a meaningful project to be reviewed and approved by a panel of advisors.
Elective Courses
CS505 Intelligent Autonomous Robotics [3 CH]
This course explores the fundamental problems involved in producing real world intelligent behaviour in robots, covering the different information processing methods and control architectures that have been developed and are currently in use, including probabilistic methods and approaches inspired by biological systems. The course is structured around a practical task to develop navigation algorithms on a real robot platform.
CS 506 Game Theory and its Applications [3 CH]
The course introduces the main concepts and tools of game theory with the aim to enable the student to read original game-theoretic literature and to prepare him/her to do research in the field. The student will learn how to represent an economic situation as a game (part 1) and how to analyze it using different equilibrium concepts proposed in the literature, the prominent one being the Nash equilibrium (parts 2 and 3). In part 4, the course concentrates on strategic interaction under incomplete information and modify the Nash equilibrium concept to include the uncertainty of the players about some of the parameters of the game. Often, an equilibrium concept fails to provide a unique solution to the game. Part 5 deals with the problem of indeterminacy in games in extensive form and introduce refinements of the Nash equilibrium. Part 6, describes some applications for Game theory.
CS507 Probabilistic Modeling and Intelligent Reasoning [3 CH]
The course covers two main areas (i) the process of inference in probabilistic reasoning systems and (ii) learning probabilistic models from data. Its aim is to provide a firm grounding in probabilistic modeling and reasoning, and to give a basis which will allow students to go on to develop their interests in more specific areas, such as data-intensive linguistics, automatic speech recognition, probabilistic expert systems, statistical theories of vision etc.The course will cover the most important topics in probabilistic modeling and unsupervised learning and neural computation, and provide a thorough basis for understanding other extensions developments and applications of Artificial Intelligence Technologies.
CS508 Advanced Expert Systems [3 CH]
This course is an introduction to expert systems. The course focuses on how theory and applications complement each other. Both theory and application are presented. Students are provided with an expert system shell which they can use to develop systems of their own. By integrating theory with a fully functional means of applying that theory to real-world situations, students will gain an appreciation for the role played by expert systems in today’s world. This course include knowledge-based intelligent systems, Rule-based expert systems, Uncertainty management in rule-based expert systems, Fuzzy expert systems and Frame-based expert systems.
CS509 Computational Intelligence [3 CH]
A selection of topics spanning a range of Computational Intelligence approaches under the following headings: Fuzzy Systems (e.g. Fuzzy Logic, Fuzzy Rule Bases, Mamdani Methods). Model-based Technology (e.g. Qualitative and Fuzzy Qualitative reasoning, model-based diagnosis). Nature Inspired Computing (eg. Neural Nets Artificial Immune Systems, Particle Swarm optimisation methods. This will include a rudimentary presentation of the basic biological principles involved). Introduction to Machine Learning (e.g. Decision Trees, concept learning, clustering.
CS510 Knowledge Engineering [3 CH]
Introduction to knowledge based system development life cycle, acquiring knowledge from domain experts, text, and data, machine learning techniques used to automate the knowledge acquisition process, knowledge modeling approaches, design and implementation of knowledge based systems, knowledge based systems verification and validation techniques.
CS511 Advanced Selected topics in Artificial Intelligence [3 CH]
Topics which are not included in the curriculum and seems to be needed. These topics are suggested as an elective subjects by the council of the computer science department.