CS7050 - Artificial Intelligence (2020/21)
Module specification | Module approved to run in 2020/21 | ||||||||||||
Module title | Artificial Intelligence | ||||||||||||
Module level | Masters (07) | ||||||||||||
Credit rating for module | 20 | ||||||||||||
School | School of Computing and Digital Media | ||||||||||||
Total study hours | 200 | ||||||||||||
|
|||||||||||||
Assessment components |
|
||||||||||||
Running in 2020/21(Please note that module timeslots are subject to change) |
|
Module summary
This module introduces the essential principles, methods and techniques in AI. It covers a broad range of topics such as search, planning, logic, knowledge representation and machine learning. It discusses examples of intelligent systems and studies how to develop intelligent applications such as expert systems, learning systems, and autonomous mobile and robotic systems. Students will be offered lectures, which introduces the important concepts, explain the principles and techniques, and demonstrate how to apply them to solve problems in the related topics. The workshops will provide practical sessions to help students understand the content of the lectures and build the necessary skills to develop intelligent systems.
Prior learning requirements
N/A
Syllabus
The main topics of the study will include:
1. Introduction to Artificial Intelligence. Definition, history and problematics of AI. Rational reasoning and intelligent behaviour. Human and Artificial Intelligence. Examples of AI systems. LO1
2. Basic logic and reasoning. Propositional logic, First-order predicate logic, Fuzzy logic. Logic Inference and other methods of reasoning. LO1-2
3. Search and Problem Solving. Uninformed search: breadth-first, depth-first, iterative deepening. Heuristic Search: Greedy search, A*-Search, IDA-Search. Empirical comparison of the search algorithms. LO1-2
4. Knowledge representation. Declarative and procedural approach. Symbolic and non-symbolic methods. Semantic nets, object-orientation and network-centric approaches. LO2-3
5. Automated reasoning. Forward chaining and backward chaining. Conflict resolution. LO2-3
6. Knowledge Acquisition. Knowledge encoding, expert system testing and expert system implementation. LO2-3
7. Natural Language Processing. Syntactic analysis, semantic disambiguation, summarisation and machine translation. Application of NLP methods to data analysis. LO1, LO3
8. Machine Learning. Supervised learning, unsupervised learning, reinforcement learning. LO1, LO4
9. Neural Networks. Computation in the brain, artificial neuron models, linear neural networks, multi-layer networks. Backpropagation. Application to classification, recognition and optimisation tasks. LO1, LO4
10. Intelligent mobile robots. Robot navigation, robots’ cooperation and competition. Multi-agent systems and robots. LO1
11. Legal, Ethical & Professional Issues in AI. AI and law. National and international regulation related to AI. Ethic of AI and impact of AI on society. LO5
Balance of independent study and scheduled teaching activity
The module will be taught by a mixture of lectures, tutorials and workshops, and self-study activities.
The lectures (2 hours) will normally be used to introduce the various concepts and principles of the module’s topics.
Each lecture will be followed by a tutorial session (0.5 hour). In the session, coursework and workshop tasks will be explained and similar tasks with solutions will be considered.
During the workshop sessions (1.5 hours), students will expand the materials from the lectures and tutorials, and practise solving programming problems (or simulation related experiment) using Java or Python/MATLAB, with examples from both the lectures and exercises set for the supervised tutorial sessions.
Students are expected to spend time on unsupervised work in the computer laboratories and in private study to do their coursework.
All lecture, tutorial and workshop materials for students will be placed on WebLearn.
Learning outcomes
On completing the module, the student will be able to
LO1 Understand and critically analyse the essential concepts, principles, methods, techniques and problems of AI.
LO2 Have working knowledge of heuristic search, qualitative and quantitative assessment and information retrieval methods and apply them to problem solving.
LO3 Demonstrate the understanding of knowledge engineering and ability to develop a simple prototype of knowledge-based systems.
LO4 Differentiate between different methods for machine learning applicable to classification, recognition and adaptation tasks.
LO5 Understand the Legal, Ethical & Professional Issues brought by AI and the impact of AI on society.
Assessment strategy
The assessment will consist of a coursework (CW) and a two-hours open book examination.
The CW will assess students’ ability to apply knowledge, principles and skills of AI to a real project [LO2-LO4]. Formative feedback will be provided during the term.
Final CW version is to be submitted at the end of the semester to get summative feedback.
The examination will test the student’s retention, understanding and insight of the material drawn from the entire module [LO1-LO5]. Any learning material, CW and logbooks will be permitted for use during the examination.
Bibliography
Core Textbooks:
• Stuart Russell, Peter Norvig, Artificial intelligence: a modern approach, global edition, 4/e, Pearson 2020, ISBN-10: 0134610997 • ISBN-13: 9780134610993)
Other Texts:
• Michael Negnevitsky, Artificial intelligence: a guide to intelligent systems, 3/e 2011, ISBN-10: 1408225743 • ISBN-13: 9781408225745.
• Mark Fenner, Machine learning with python for everyone, Pearson 2020, ISBN-10: 0134845625 • ISBN-13: 9780134845623
Journals:
IEEE Intelligent Systems,
IEEE Artificial intelligence,
IEEE Xplore: IEEE Intelligent Systems
Websites:
https://www.tutorialspoint.com/artificial_intelligence_with_python/index.htm
Electronic Databases: ACM Digital Library, IEEE Xplore/IET Digital Library