CS3S668 - Intelligent Systems 01 Sep 2022 - 31 Aug 2028 | Version 4
Associated Module Information
| Module Code: | CS3S668 | ||
|---|---|---|---|
| Module Title: | Intelligent Systems | ||
| Faculty: | Faculty of Computing, Engineering and Science | ||
| Faculty Group: | Computing and Mathematical Sciences | ||
| Faculty Sub Group: | Computer Science | ||
| Module Leader: | Christopher Tubb | ||
| Module Team: | |||
| First Intended Intake: | SEP 2017 | Final Year of Intake: | |
| Date Closed: | |||
| Credit Value: | 20 | Credit Level: | 6 |
| Language: | English | ||
| Percentage of Module Taught in Welsh: | 0 | ||
| Equivalent Module: | |||
| HECOS codes: | 101020 - computer games programming | ||
| HECOS Code Weighting: | 100 | ||
Document Version Information
| Version | 4 |
|---|---|
| Valid From | 01 Sep 2022 |
| Valid To | 31 Aug 2028 |
Module Aims
To provide a broad theoretical and practical introduction to artificial intelligence and the design and development of intelligent systems.
Content Summary
The nature of intelligence, intelligent behaviour, example problems, problem characteristics, agents.
Search: problem spaces, iterative improvement, uninformed and informed search, heuristics, space and time efficiency of search, combinatorial explosion of search space, stochastic search, metaheuristics, A* search.
Knowledge representation and reasoning: logic (classical propositional logic, first-order predicate logic dealing with uncertainty and fuzzy Logic, probability, and modelling uncertainty), forward and backward chaining, probabilistic reasoning, issues, rule-based systems, semantic networks, planning.
Machine Learning: definitions and examples, inductive learning, statistical based learning, over-fitting, measuring accuracy, supervised learning, nearest neighbour algorithms, unsupervised learning, applications of machine learning.
Agents: definitions, architectures, software agents, agent learning, multi-agent systems.
Ethical, societal and commercial considerations.
Learning and Teaching Methods
| Activity Type | Hours |
|---|---|
| Lecture | 12 |
| Practical classes and workshops | 24 |
| Independent Study | 35 |
| Directed Study | 44 |
| Formative Assessment - Independent | 26 |
| Groupwork | 24 |
| Problem / challenge based learning | 35 |
| Total Hours Selected | 200 |
Learning Outcomes
| # | Learning Outcome |
|---|---|
| LO1 | Demonstrate knowledge, comprehension and discernment of AI paradigms in the context of common problems and of ethical, legal and commercial issues. |
| LO2 | Synthesize effective AI based solutions to specified problems |
Module Requisites
| Code | Title | Requisite Type |
|---|---|---|
| MOD008936 | Data Structures and Algorithms with Object Oriented Programming | pre-requisite |
Assessment Criteria
| Assessment Category | Assessment Type | Description | Duration | Word Count | Weight (%) | Best of? | Pass Mark |
|---|---|---|---|---|---|---|---|
| Asynchronous Assessment | Practical Written Work 1 | A write up of a piece of practical work that has been | 0 | 2000 | 50 | No | 40 |
| Asynchronous Assessment | Poster 1 | A two- or three-dimensional visual representation of information on a specific topic, aimed at a particular audience without the need for the author's presence. | 0 | 2000 | 50 | No | 40 |
Assessment Matrix
| Assessment Type | Learning Outcomes | ||
|---|---|---|---|
| LO1 | LO2 | ||
| Practical Written Work 1 | ✔ | ✔ | |
| Poster 1 | ✔ | ✔ | |