|
|
|
|
|
|
|
|
|
Dynamic belief network
Глоссарий по искусственному интеллекту |
See: dynamic probabilistic network. dynamic probabilistic network (dpn) this type of network is a special case of a hidden markov model (hmm). the hidden states of the hmm are decomposed into the product of several different subspace of states, and changes in the product space are assumed to occur along exactly one dimension at time. as an example, suppose we wish to model the views of a robot moving through a plant with 15 possible locations and 4 possible views through its cameras. then, a general hmm would consider only 15*4 or 60 states, while a dpn might assume that, at each time step, the robot could change either its location or viewpoint, and attempt to model it as a two-dimension (location x viewpoint) walk. these models are also known as dynamic belief networks or factorial hidden markov models (hmms). see also: hidden markov model.
|
|
Probabilistic, английский
- Вероятностный
- Attribute of non-deterministic systems whose transitions between states follow known or ascertainable probabilities (->probability). the ergodic behavior of probabilistic systems is describable as a markov chain. probabii.ity
Decomposed, английский
|
Dart and dartmap, английский
See: distributed art and artmap.
Edr project, английский
See: electronic dictionary research project.
|
|
|
|
|
|
|