Re: computer-go: Insight of a human continued

[Christian Nentwich <c.nentwich@xxxxxxxxxxxx>]

> > >trying to play like a human player. Human players use patterns to
> > >consider whole candidate sequences instead of single moves, e.g. this
> > >white crosscut happens a lot
> > Many Faces also associates sequences of moves with patterns.
> In the early days, Goliath also used sequences. The main reason was that my
> evaluation function was very expensive and by using sequences I could get
> away with skipping evaluation of the internal nodes. I found it too
> inflexible however, leading to some very stupid plays in situations where
> the sequence matched but was highly inappropriate. So as soon as my

But then getting rid of the sequences again is surely only one solution.
Since human players do think in terms of sequences in quite a few
situations, I wonder if the evaluation function was the weak point
rather than the method of using sequences. 

After all, if the result is bad the sequence should not have been chosen
at all but a fall-back to normal reading is necessary.

Christian