You can find an overview of my main current research topic, the Turing-inspired
Meta-Morphogenesis project, here:
It has many sub-problems that are likely to remain unsolved for years to come.
My main web page with more information about me is here:
Previous work on the Cognition and Affect project, exploring biologically plausible architectures for intelligent agents (and capable in principle of explaining affective states and processes, including desires, preferences, values, anger, fear, etc.) can be found here: http://www.cs.bham.ac.uk/research/projects/cogaff/
I am no longer involved in teaching and therefore will not normally be supervising student projects, though I am prepared to consider proposals from students who have an idea that is closely related to my interests.
If you have a relevant idea you can try to persuade me to supervise you. Since I do a lot of work at home, please email me at firstname.lastname@example.org if you wish to meet and talk (in room UG34, which I share with two other researchers).
I would be willing to consider supervising a very bright student (with first
class grades) who has had practical experience of ARM machine code, and compiler
design, and who knows pop11, and who would be interested in a project to port
Poplog to ARM+linux, so that it could be run on a RaspberryPi, for example. This
might be too much for one student. A team of two or three students dividing the
work might be better. If two or more students are involved, part of the project
might be updating the Poplog AI teaching files, some of which are linked here:
For video tutorials see:
Moreover, I am unwilling to supervise projects based on programming languages on which I am not an expert, since otherwise I will not be able to give good advice, and help with debugging will take far more time and effort.
That means I normally expect students supervised by me to use Pop11, which I know very well or perhaps Prolog which I don't know so well, or maybe Lisp, which I know a little.
In particular I don't want to supervise projects based on languages that were not designed specifically to support AI, as I think they make the tasks too difficult, and constrain what can be achieved.
The Poplog system which contains several AI languages and the SimAgent
toolkit is now available free of charge from here:
The latest version, for linux, is here:
More on the CogAff Project, including papers
(Probably out of date now!)
and many of my recent research papers can be found here http://www.cs.bham.ac.uk/research/cogaff/
And recent research presentations, at conferences, etc. here: http://www.cs.bham.ac.uk/research/cogaff/talks/
If you browse these files you'll get some idea of my expertise and interests. There are also many suggestions for possible topics listed in online TEACH files, accessible from VED, e.g. TEACH PROJECTS (though many of those would be too elementary for a final year or MSc project.)
I do not wish to supervise projects involving neural nets or evolutionary computation (e.g. Genetic Algorithms), since I don't know enough about them to give good advice on technical details, and I am probably not a good person to supervise projects involving evolutionary computation. I am willing to consider other sorts of evolutionary investigations.