module specification

Artificial Intelligence (AI) is one of the most important sub-fields of Computer Science and has a high profile with respect to popular recognition of activities associated with Computer Science. This module introduces the essential principles, knowledge and methods in AI. It also looks into several major application domains of AI. These application domains include expert systems, neural networks, and mobile robot systems. Each lesson introduces the important concepts, explains the principle and techniques of the related topics, and provides practice workshops to help students to understand the contents of the lectures.

Computing & computer science in a BSc course

The main aims of the module are:
To provide students’ basic concepts, knowledge and techniques in the AI and Neural networks in general, logic, reasoning, knowledge representation and search approaches in particular.
To broaden students’ knowledge though applying the AI principle to expert systems and mobile robot systems.
To give students an awareness of the issues involved in building such systems.

1. Introduction to Artificial Intelligence
   What Is Artificial Intelligence? Introduce the history of AI, Knowledge-Based Systems, Neural networks, etc.
    
2. Basic logic and reasoning
   Propositional logic, First-order Predicate Logic, Fuzzy logic and other methods for reasoning
    
3. Search and Problem Solving
   Uninformed Search: Breadth-First Search, Depth-First Search, Iterative Deepening, and Comparison.Heuristic Search: Greedy Search, A*-Search,  IDA-Search, Empirical Comparison of the Search Algorithms, etc.
    
4. Expert systems and knowledge based systems
   Basic concepts in expert systems and knowledge based systems: What is an expert system? Introduce the structure of Expert Systems and application of expert system.
   Knowledge representation:
   Expert System Reasoning: (Forward Chaining: Data oriented, Backward Chaining: Goal oriented and Conflict Resolution: Select rule to applicant.)
   Development of Expert Systems: (Knowledge Acquisition, Knowledge Representation, Knowledge Encoding, Expert System Testing and Expert System Implementation.)
    
5. Neural networks
   Basic concepts in neural networks: (Computation in the brain, Artificial NeuronModels, Linear regression, Linear neural networks, Multi-layer networks and Error Backpropagation)
   Application in Classification;
   Optimizing Linear Networks;
   The Backprop Toolbox;
   Unsupervised Learning;
    
6.  AI application
   Intelligent mobile robot navigation;
   Multiple robots cooperation and competition;
   Multiple agents and robots;
   And other application examples;

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 materials got during the lectures and tutorials, and practice solving programming problems (or simulation related experiment) using Java or 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.

On completing the module the student will be able to
• Understand the essential concepts, principles, techniques and problems of AI.
• Demonstrate the understanding of basic logic, search and reasoning approaches and apply them to problem solving.
• Demonstrate the understanding of knowledge representation and knowledge based systems.
• Acquire knowledge of neural networks, intelligent mobile robot navigation and other intelligent system application areas.

The assessment will consist of a coursework (CW) and a two-hour open book examination.
The CW will be assessed on students’ ability to apply knowledge, principle and skills of AI to real project. The draft report will be submitted in week 11. The formative feedback will be given. The Final CW version to be submitted in the end of the semester to get summative feedback.
The examination will test the student’s retention, understanding and insight of material drawn from the entire course. Any module learning material, CW and logbooks may be used during the examination.

Books:
• Wolfgang Ertel, Introduction to Artificial Intelligence, 1st Edition: Springer, 2011, ISBN: 978-0-85729-298-8,
• Rob Callan, 2003, Artificial intelligence, Palgrave, ISBN: 9780333801369
• Introduction to Autonomous Mobile Robots (second edition), Roland Siegwart, Illah R. Nourbakhsh and Davide Scaramuzza. Bradford Books, 2011. ISBN 0262015358, http://classes.engineering.wustl.edu/cse550/
• Simon Haykin,  2009, Neural Networks and Learning Machines,  Pearson, 3rd Edition,  ISBN13: 9780131293762,   ISBN10: 0131293761
• Keith Darlington, 1999, The Essence of Expert Systems, Pearson, SBN13: 9780130227744, ISBN10: 0130227749