|Delivery Type||Delivery length / details|
|Seminars / Tutorials||2 seminars on the assignment|
|Assessment Type||Assessment length / details||Proportion|
|Semester Exam||2 Hours STANDARD 2 HOUR EXAMINATION||70%|
|Semester Assessment||WRITTEN ASSIGNMENT BASED ON COURSE MATERIAL||30%|
|Supplementary Assessment||Will take the same form, under the terms of the Departments policy||100%|
Write simple programs in Java to search for solutions using the AI techniques discussed in the module.
Demonstrate an appreciation of at least one application of each AI method that they have studied.
Demonstrate an understanding of the learning methods discussed in this module.
This the first of two modules that introduce the foundational principles of Artificial Intelligence (CS26210 is the second part). For those on GG4R / GG47 and GH76 / GH7P it is a core component on top of which the rest of the AI and Machine Learning material is built, for students on other degree schemes, it provides material that illustrates algorithm development and issues of time complexity.
This module begins with a motivational section on the use of AI in computer games programming: one of the cutting-edge applications of AI in use today. It then focuses on the foundational issue of search (finding solutions to problems) and introduces some basic, but important, learning methods.
What is required to get computers to produce games AI?
Using AI and agents as a principle for this module.
Applications of AI such as bioinformatics, business and robotics.
Using minimax as an example of simplified game playing.
2. Uninformed Search [3 lectures]
Depth- and breadth-first search.
3. Informed Search [3 lectures]
Greedy/best-first search, A*search.
4. Evolutionary Computation for Search and Optimisation [3 lectures]
Genetic algorithms and the four GA operators:
- evaluation and the fitness function
- selection (tournament and routlette wheel selection)
- crossover (various types)
5. Clustering [4 lectures]
Overview of other clustering methods (Gaussian, fuzzy etc).
6. Case-based reasoning and k-nearest neighbour [3 lectures]
Introducing the idea of learning from data,
(transductive learning, not inductive learning),
Choosing the value of k,
Weighting the k members' contribution.
|Skills Type||Skills details|
|Communication||During the seminars, students will be encouraged to `brainstorm¿ and communicate between themselves and with the lecturer.|
|Improving own Learning and Performance||In order to solve the problem in (1), using the research from (2), students will improve their abilities in `learning to learn¿.|
|Information Technology||Use of IT will be vital for the completion of this module.|
|Problem solving||The assignment will require students to apply their newly gained AI knowledge to a problem. Only the outline of the solution will be give, so that the student must solve the details of the problem themselves.|
|Research skills||Required to solve the problem in (1)|
This module is at CQFW Level 5