Research Report - Intelligent Systems
This group is interested in a variety of areas of research involving intelligent systems and computational intelligence. In many ways, intelligent systems research is at the interface of humans and computers. Generally speaking, the goals of intelligent systems research are: (i) To produce computer software and hardware that is capable of intelligent behaviour and/or problem solving, (ii) To model aspects of human intelligence using computational techniques, and (iii) To investigate the interaction between humans, sensory information from the environment, and computer systems.
Much of the work of the group is in the realm of computational intelligence which is concerned with the development of algorithms and problem-solving techniques in areas such as supervised and unsupervised learning, optimization, pattern recognition and function approximation. The application of this technology is often to problems that are difficult to solve with conventional computing methods, yet are accomplished easily by humans. In other cases, the aims are to relieve humans from tedious or hazardous tasks, as well as solving problems where exact solutions are not possible and effective approximate methods are desirable.
One specific approach is through the use of Artificial Neural Networks (ANNs), which are computing devices designed to emulate some of the learning processes that are believed to take place in the brain. In the last decade or so ANNs have emerged as powerful computational techniques for identifying patterns in data and for predicting future events, and have been widely successful in solving many problems in engineering and information technology. In recent years, statistics and computational learning theory have given this field a more solid theoretical foundation and produced a number of powerful modelling techniques and algorithms that are being investigated by the group. These include Support Vector Machines, the technique of boosting and other methods for combining machine learning models. Probabilistic modelling methods such as Bayesian networks and graphical models have also created recent interest in relation to machine learning and evolutionary computation.
Outcomes from this work can provide new approaches for another very active area in the group, namely robotics, where methods developed in computational intelligence are implemented in computer hardware. Also in the robotics area, broader studies relating to the behaviour of biological brains are being undertaken to assist in the development of new sensing and locomotion schemes to enable intelligent systems to interact with real world environments. In addition, research into navigation and cooperation between robots in a dynamic and visually noisy environment is being conducted through practical applications such as robot soccer. More generally, the research aims to address a number of mechanical, electronic and computer systems issues.
An area closely related to computational intelligence is that of evolutionary computation which, when coupled with probability modelling can be applied to some important problems in optimization. In the past, such methods have been widely applied to discrete optimization problems, but in our group, we are seeking to develop methods for dealing with problems where the variables are continuous. This will very much broaden the range of applicability of these techniques. The aim is to develop algorithms that uniquely learn the structure of a given problem solution space and exploit this structural knowledge to seek out a global optimum. These algorithms will be applicable to practical optimization problems that are known to be difficult. They will also advance knowledge fn the theoretical and dynamical properties of these kinds of technique.
The final area of research in this group is cognitive science, which is a rapidly expanding, interdisciplinary field of study aimed at understanding the mental processes that underlie cognitive abilities. Its defining technique is to bring expertise gained from the disciplines of computer science, psychology, linguistics, neuroscience and philosophy to bear on a set of common questions: (i) What are the basic components of cognitive processes? (ii) Are they subsumed by a common mental mechanism? (iii) What is the relationship between the physical apparatus and cognition? To answer these questions cognitive scientists engage in empirical and conceptual studies aimed at assessing their formal and computational models of various aspects of cognition. The sorts of areas investigated include the information-acquisition and information-processing mechanisms underlying cognitive abilities like perception, recognition, information storage and information retrieval, language acquisition, comprehension and production, concept acquisition, problem solving, and reasoning. Cognitive science is concerned with modelling and understanding aspects of human intelligence via computer simulation, evolutionary algorithms, game playing, human memory, learning dynamics, language learning and cognitive neurophyschology.
Associated Staff
Prof Tom Downs
Prof Peter Eklund
Dr Marcus Gallagher
Dr Mark Schulz
A/Prof Janet Wiles
Dr Gordon Wyeth
<%@ include file="/include/footer.inc.jsp" %>