An introduction to modern AI representation systems and problem-solving techniques.
|Paper title||Artificial Intelligence|
|Teaching period||First Semester|
|Domestic Tuition Fees (NZD)||$1,080.30|
|International Tuition Fees (NZD)||$4,858.95|
- COSC 242
- Schedule C
- Arts and Music, Science
Computer Science Adviser (firstname.lastname@example.org)
- More information link
- View more information about COSC 343
- Teaching staff
- Lecturer: Dr Lech Szymanski
- Paper Structure
In this paper we will look at some different definitions of intelligence and at the concept of intelligent agents. As a way of focusing on the hard problems to be solved in AI, we will do some practical work with LEGO robots, concentrating on the issue of how to get information about the world and how to make use of it. We will consider techniques for machine learning and probabilistic reasoning. Almost every human ability results from learning from experience: we will look at how these learning processes can be modelled computationally.
Topics to be considered include:
- Embodied AI and robots
- Machine learning algorithms (with a focus on neural networks)
- Search and optimisation algorithms (including genetic algorithms)
- Probabilistic reasoning method (including Bayesian methods)
- Natural language processing
- Two assignments 40%
- Final exam 60%
- Teaching Arrangements
- There are two lectures per week, plus weekly lab or tutorial sessions.
- Artificial Intelligence A Modern Approach (Third Edition) , by Stuart Russell and Peter Norvig, Prentice Hall 2010.
- Course outline
- View the course outline for COSC 343
- Graduate Attributes Emphasised
- Interdisciplinary perspective, Scholarship, Communication, Ethics, Teamwork.
View more information about Otago's graduate attributes.
- Learning Outcomes
- Students will gain an understanding of some of the core concepts in symbolic AI research: autonomous agents, planning and search, logical knowledge representation formalisms, grammars for representing knowledge of natural language
- Students will gain an understanding of some of the core concepts in sub-symbolic AI research: sensory perception, motor control, machine learning, decision trees, neural networks
- In each case, this understanding will be strengthened through practical exercises and experience with implemented systems
- The paper will also give students an awareness of the increasing influence of these technologies in daily life