Course - Adaptive Neural Networks - IT8008
Adaptive Neural Networks
New from the academic year 2011/2012
About
About the course
Course content
This course will be given when a) there are PhD students with the appropriate combination of competence and interest, and b) the main teacher is not on sabbatical, or on sabbatical but being replaced by another teacher.
The course delves deeply into artificial neural network (ANNs) that can alter their own performance, either via learning or evolutionary methods, or a mixture of the two. The main application platform for these ANNs is intelligent agents, and the textbook "Evolutionary Robotics" will be read by all students at the beginning of the course.
Students will learn to implement adaptive ANNs and to use them as controllers for intelligent agents.
Learning outcome
Knowledge: Students will learn advanced neural network methods, with special focus on adaptive mechanisms.
Skills: Students will be able to implement (from scratch) neural networks that both reason and learn, and which can be used as controllers for simple agents, e.g. robots.
General Competence: Students will acquire enough theoretical and practical experience with adaptive neural networks to a) write a high-level scientific article about the various types of adaptive neural networks, b) judge the applicability of diverse network types as solutions to different practical problems, and c) implement these solutions.
Learning methods and activities
Students will read the book "Evolutionary Robotics" and other related articles. They will then have the opportunity to implement their own adaptive-ANN control system for a simulated robot (using Webots or a similar package).
Students will write a report of approximately 10 pages describing their system, which they will also demonstrate at the end of the course. Students can choose to forego the implementation in exchange for a longer report (of approximately 20 pages) giving extensive coverage of the state-of-the-art in adaptive-ANN-controlled intelligent agents.
Recommended previous knowledge
IT1105/TDT4120 Algorithms and Data Structures
MA0301 Elementary Discrete Mathematics
IT3708 Subsymbolic AI Methods
Required previous knowledge
At least one course in computer programming plus at least one university-level course in mathematics. TDT4136 (Logic and Reasoning Systems) or a similar AI-Introduction course from another university.
Course materials
The book "Evolutionary Robotics" must be purchased by each student. Other research articles will be distributed during the semester.
Subject areas
- Informatics
- Technological subjects