- Markov random fields provide a convenient method for representing
dependencies as well as a search methodology in a fixed site space
- modeling as a Gibbs distribution yields a dramatic decrease in
computations - for an 8x8 block image and 5 states we needed
564 computations, now we need 5*64*iterations
- it is unclear how/if this could be used for a real-time system
in speech; pre-segmenting the data would be necessary
- a natural fit for the object recognition portion of our
USFS project