School of Electronics and Computer Science:
COMP6031 Foundations of Artificial Intelligence
Basic Information
| School | |
|---|---|
| Known as | COMP6031. |
| Session and Semester | Semester One, 2011 - 2012 |
| Credit | 20 Credit Points |
| Unit Leader | Dr Richard A. Watson |
| Moderators | Klaus-Peter Zauner |
| Study | 200 hours total |
| Assessment | 50% examination, 50% coursework |
| Coursework | Implementing Classic AI Algorithms |
| Teaching | 40 lectures, including 8 laboratory sessions |
| Referral | On referral, this unit will be assessed 100% by examination. |
| Syllabus Approved |
Description
Aims
This unit aims to give a broad introduction to the rapidly-developing field of artificial intelligence (AI) covering a range of approaches (modern, classical, symbolic, and statistical). This should prepare students for specialist options in semester 2. In addition, the laboratories and in-class discussions should help to build up the cohesion and morale of the MSc Artificial Intelligence cohort.
Learning Outcomes
Knowledge and Understanding
Having successfully completed the module, you will be able to demonstrate knowledge and understanding of:
- classical and modern approaches to AI
- the principal achievements and shortcomings of AI.
- the main techniques that have been used in AI, and theirrange of applicability
- the philosophical basis of AI
- future challenges and likely future developments in AI
Intellectual Skills
Having successfully completed the module, you will be able to:
- implement classical AI algorithms
- apply modern statistical approaches to AI
- develop intelligent frameworks for problem solving
- assess the claims of AI practitioners as they relate to 'intelligence'
- assess the validity of approaches to modeling intelligent processing
- assess the applicability of AI techniques in novel domains
General Transferable (key) Skills
Having successfully completed the module, you will be able to:
- read and understand complex technical material
- employ critical-thinking skills
- manage your time effectively
Topics Covered
- Introduction to AI
- Flavours of AI: strong and weak, neat and scruffy, symbolic and sub-symbolic, knowledge-based and data-driven.
- The computational metaphor. What is computation? Church-Turing thesis. The Turing test. Searle's Chinese room argument.
- Programming Languages for AI
- Declarative Programming using Prolog
- Scientific programming and statistical analysis using Matlab
- Search
- Finding satisfactory paths: depth-first and breadth-first, iterative deepening, evolutionary algorithms, hill-climbing and gradient descent, beam search and best-first. Finding optimal paths: branch and bound, dynamic programming, A*.
- Representing Knowledge
- Production rules, monotonic and non-monotonic logics, semantic nets, frames and scripts, description logics.
- Reasoning and Control
- Data-driven and goal-driven reasoning, AND/OR graphs, truth-maintenance systems, abduction and uncertainty.
- Reasoning under Uncertainty
- Probabilities, conditional independence, causality, Bayesian networks, noisy-OR, d-separation, belief propagation.
- Machine Learning
- Inductive and deductive learning, unsupervised and supervised learning, reinforcement learning, concept learning from examples, Quinlan's ID3, classification and regression trees, Bayesian methods.
Teaching and learning activities
Teaching methods include
- Lectures and discussion sessions
- Laboratory classes covering declaring programming using Prolog, andscientific programming and statistical analysis using Matlab
Learning activities include
- classroom discussion to develop critical analytical and summary skills
- a major coursework assignment involving the application of a number of classic AI algorithms and techniques to solve a real-world problem such as route planning in a maze
- revision for the examination
Methods of assessment
| Assessment method | Number | % contribution to final mark |
|---|---|---|
| Presentations [cwork] | 2 | 15 |
| Programming Assignment [cwork] | 1 | 35 |
| Examination [exam] | 1 | 50 |
Feedback and student support during module study
Students are given immediate feedback on their laboratory work, which is graded at the end of each session.
The coursework assignments are marked within 3 weeks of submission and feedback is provided individually and to the class as a whole.
Relationship between the teaching, learning and assessment methods and the planned learning outcomes
The knowledge and understanding skills listed above will be taught in lectures. The intellectual skills will be taught through applications of the AI techniques covered in laboratories and developed through the assignment. The transferable skills are not implicitly assessed through the advanced and intensive nature of this module.
The purpose of the exam is to test understanding of topics that it is difficult to assess fully in an assignment.
Resources
Core Resources
- Russell, S and Norvig, P Artificial Intelligence: A Modern Approach (2nd Edition), Prentice Hall 2003. [Library] [Shops]
Taught to
COMP6031
MSc in Artificial Intelligence (Compulsory)Students who are not registered on an ECS approved programme may take this module subject to meeting its pre-requisites and the availability of resources. To confirm this, please can you contact the module leader (as listed above) in the first instance. They will then refer you on to the appropriate director of studies for formal approval of your selection.