Computational Intelligence and Cognitive Science (Computing)
We pursue a range of research interests that relate to Artificial Intelligence & Cognitive Science. In particular our areas of interest include robotics, adaptive intelligent systems, the modelling and evaluation of human perception (hearing, speech and vision) and real-time image analysis and computer vision. In general we seek a better understanding of complex systems and the principles that underly their emergent properties and ultimately give rise to cognition.
Some of our current and recent research activities are outlined below.
Projects
Unbounded evolution (for computational intelligence)
Alastair Channon presented the first (and so far only) closed artificial system to pass the established statistical "ALife Test" for unbounded evolutionary dynamics: an achievement identified by Bedau, Snyder and Packard as "among the very highest priorities of the field of artificial life". Earth's biosphere (through fossil-record databases) is the only other system to have passed, although many have been evaluated. This is a very significant result: we can now begin to draw generalized conclusions about open-ended evolution that were previously impossible given just the real-world example. It significantly advances our ability to generate emergent processes and structures, including complex and intelligent ones. In related work he introduced significant improvements to the test, making it well-grounded even for long-term unbounded evolution in artificial systems, through the first ever method of computing individual genes' adaptive ('normalized') evolutionary activities.
Extending the capabilities of neuro-evolutionary systems
In collaboration with his MSc students, Alastair Channon has worked on the evolution of artificial neural controllers that solve tasks requiring deliberative behaviours: tasks that cannot be solved by reactive mechanisms alone and which would traditionally have their solutions formulated in terms of search-based planning. The results of this work have demonstrated the first incremental neuro-evolutionary learning on increasingly complex versions of such tasks. Related work, with Thomas Miconi (his PhD student), was the first to demonstrate realistic co-adapted behaviours in co-evolved physically simulated articulated creatures using general purpose neurons: removing a previous barrier to the long-term evolution of new, emergent behaviours.
Holonic Manufacturing Systems
Thomas Neligwa has worked with a large industry-led international Holonic Manufacturing Systems (HMS) project with major industrial partners including DaimlerChrysler (Germany), Toshiba (Japan), Rockwell Automation (USA), and many academic institutions from across the world. The aim of the HMS project is to develop modern and intelligent approaches to manufacturing control in order to accommodate low-volume, high-variety manufacturing requirements. This is one of the major objectives of a larger international group known as the Intelligent Manufacturing Systems consortium.
Robot Navigation
Theocharis Kyriacou has worked on vision-based urban navigation procedures for verbally instructed robots. This work contributes to the wider field of instruction-based learning for mobile robots: looking into the design of robots that understand and follow unconstrained natural language instructions.
EPSRC "Think Crime" Grant
In collaboration with Peter Haycock (iEPSAM), KP Lam (iEPSAM) and Tony Kearon (Criminology) this two-year EPSRC grant has funded an RA to carry out research into improved processing of X-ray scanner images. In particular we have been using neural networks to identify specific elements that were present in the target of the X-ray beam.
Syntactic Pattern Recognition
Peter Fletcher is working on an algorithm for recognising recursively structured geometric patterns in the presence of noise, geometric distortion, and overlapping patterns. This occurs in the context of a long-term research programme into connectionist architectures for robust symbol processing.
Mining Astrophysical Datasets
In collaboration with Pierre Maxted (iEPSAM) we secured a Nuffield Foundation Student Bursary for one of our MSci students, Andrew Dickinson, to investigate how neural networks could be used to classify data from SuperWASP observations of the night sky.
Post-stroke impairment
Along with David Pandyan (iLCS) and Peter Jones (iSTM), Charles Day is helping to supervise Shweta Malhotra's stroke-impairment research. Shweta aims to compare the effectiveness of regression models and neural networks in predicting the impairment of upper-limb function, in patients that have recently suffered a stroke.
Colo-rectal Cancer Predictors
Colleagues from Crewe's Leighton Hospital, have provided Charles Day with some anonymised colo-rectal cancer case-data: to see if neural networks can be used to provide good predictors of treatment outcomes.
People
Research Assistants: Dr Jim Austin, Shweta Malhotra
Research Students: John Butcher