[MUD-Dev] Neural Networks as the AI system for a MUD?
hhs at cbs.dtu.dk
Tue Dec 7 11:20:42 New Zealand Daylight Time 1999
On Mon, 6 Dec 1999 PartyG2816 at aol.com wrote:
> Hmm, hidden markov models?
Sort of probabilistic context free grammars. Much like Andrew Norman=20
said about state machines, but with probabilistic transition states.=20
The HMM will answer which path in the model that a sequence of states=20
most likely (given state transition probabilities) would have=20
followed. It's sort of a loose description i know :-). Also a models=20
state transition probabilities can be build from examples.
Hans Henrik St=E6rfeldt | bombman at diku.dk | work: hhs at cbs.dtu.dk=
address: |___ +45 40383492 __|__ +45 45252425 =
Dybendalsvej 74 2. th, | Scientific programmer at Center for Biological =
2720 Vanl=F8se, Danmark. | Sequence Analysis, Technical University of D=
MUD-Dev maillist - MUD-Dev at kanga.nu
More information about the MUD-Dev