[EMAIL PROTECTED] wrote: > How can you call it 'intelligence' if a person limits one's thoughts and > viewpoints to a narrow domain? > Yes, I agree. It really took some imagination and open mindedness to discover UCT and Monte Carlo since it breaks so sharply away from the old traditional way of writing a go program.
It's still not clear to me what the ultimate approach is. It could be that a properly written classical program can compete - such as the approach David Fotland is using where global search is an important component to an already knowledge rich program. These are all intelligent approach as far as I am concerned. You see that the programs continue to expand to utilize resources better and continue to improve slowly but surely. It's not uncommon in computer science and mathematics to eventually see many methods as a special case of some generalization. All approaches that are producing farily strong programs have a search component and an evaluation component mixed in different ratios. We just like to get hung up on the exact implementation details and imagine that different approaches have nothing in common. - Don > DL > > > > Although interesting, I would hardly call that 'intelligence' :-) > > > > > > > > ________________________________________________________________________ > More new features than ever. Check out the new AOL Mail ! - > http://webmail.aol.com > > > ------------------------------------------------------------------------ > > _______________________________________________ > computer-go mailing list > [email protected] > http://www.computer-go.org/mailman/listinfo/computer-go/ _______________________________________________ computer-go mailing list [email protected] http://www.computer-go.org/mailman/listinfo/computer-go/
