I know that might sound crazy, but it is working towards the eventual
goal of creating feature extractors for Go positions. By learning to
map Go positions as an array of stones to Go positions as graphs of
strings (instead of just mapping them with a hand coded algorithm) I
can take intermediate results in the learner's computation and use it
as a feature for another learner.
Sounds interesting. I was thinking about learning graph patterns from
pro games for a while, but I guess the difficult thing is mastering the
complexity of comparing graphs. If you can past that somehow I would
guess that string-based pattern matching will be far better than "flat"
patterns, if that's the thing you want to do. But I don't really
understand how you want to do the mapping and what you want to do with
the graph.
Anyways, good luck with it =)
_______________________________________________
computer-go mailing list
[email protected]
http://www.computer-go.org/mailman/listinfo/computer-go/
