- Dr David Wakeling (Senior Lecturer, Computer Science/Director of Education Computer Science - University of Exeter)
|Delivery Type||Delivery length / details|
|Lecture||28 x 1 Hour Lectures|
|Practical||2 x 1 Hour Practicals|
|Assessment Type||Assessment length / details||Proportion|
|Semester Exam||2 Hours Written Exam||60%|
|Semester Assessment||Written Assignment: 30 hours||40%|
|Supplementary Exam||2 Hours||60%|
|Supplementary Assessment||Resubmission of failed/nonsubmitted coursework components or ones of equivalent value.||40%|
1. Write simple programs to solve problems using an AI technique discussed in the module.
2. Demonstrate an understanding of the search techniques discussed in this module.
3. Demonstrate an understanding of evolutionary algorithms and swarms.
4. Describe the importance of propositional and predicate logic in Artificial Intelligence systems and solve simple problems.
5. Apply data mining algorithms to data and interpret the results.
6. Explain the function and use of fuzzy logic.
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. The key concept of knowledge representation is introduced, followed by a variety of representational techniques including logic and fuzzy logic. It then focuses on the foundational issue of search (finding solutions to problems and games), naturally followed by evolutionary algorithms, optimisation and swarms. The course finishes with the use of AI techniques for data mining.
What is required to get computers to produce AI? Philosophical debate and ethical issues. Applications of AI such as games, bioinformatics, business, robotics.
2. Knowledge Representation and Logic
Symbolic and sub-symbolic representations, logical representation for problem solving.
3. Fuzzy Logic
Fuzzy sets and rules. Fuzzy inference.
Searching for solutions using both uninformed and heuristic search.
5. Optimisation with Evolutionary Algorithms and Swarms
Evolutionary algorithms, selection mechanisms, variation operators. Swarm intelligence.
6. Data Mining
Overview of data mining. KNN classification. K-means clustering. Hierarchical clustering.
7. AI in Research
|Skills Type||Skills details|
|Application of Number||Many AI techniques require number application.|
|Communication||Written skills needed for the written assessment.|
|Improving own Learning and Performance||Written assignment requires self-motivated study and work.|
|Information Technology||Inherent in the topic.|
|Personal Development and Career planning||Will feed into students' future career plans.|
|Problem solving||Written assignment promotes and assesses this.|
|Research skills||Assessing AI techniques for use in the written assignments requires reading and researching other materials.|
|Subject Specific Skills||AI techniques|
This module is at CQFW Level 5