computer-go: Neural network minimax hybrid paper

["Julian Churchill" <jjc97c@xxxxxxxxxxx>]

Hi,

 I just came back from presenting my paper at a conference and it seemed to
go down quite well, so I wondered if anyone here might be interested in
having a look. The title is "A new computational approach to Go", which
doesn't really give away much, so here is the abstract:

 "This paper investigates the application of neural network techniques to
the creation of a program that can play the game of Go with some degree of
success. The combination of soft AI, such as neural networks, and hard AI
methods, such as alpha-beta pruned minimax game tree searching, is attempted
to assess the usefulness of blending these two different types of artificial
intelligence and to investigate how the methods can be combined
successfully."

 You can get it here
http://ducati.doc.ntu.ac.uk/uksim/dad/webpagepapers/Game-14.pdf

 This isn't the full version, but is the conference version. If anyone is
further interested, please email me and I will organise something so you can
get hold of the full paper, but I currently have no webspace.
 The conference was Game-On 2001 and I was suprised by how interested people
there were about Go. There was a second Go paper at the conference, called
"A Learning Architecture for the Game of Go" by a chap called Alex Meijer,
all to do with the combinatorial game theory approach which all looked very
good.

 Any comments about the work I have done so far would be much appreciated as
the work outlined above maybe extended to a PhD level investigation.

 Cheers,
 Jules


_________________________________________________________
Do You Yahoo!?
Get your free @yahoo.com address at http://mail.yahoo.com