Inference using junction tree representation can be
performed in a "semi-parallel" fashion. The following work
suggests ways to organize/optimize the computation. The focus of
the work is on multiagent inference, but the technique is applicable
to your task as indicated in Section 10.2 of the paper.
Y. Xiang. A probabilistic framework for cooperative multi-agent
distributed interpretation and optimization of communication.
{\em Artificial Intelligence}, 87(1-2):295--342, 1996.
Yang
Y. Xiang, Ph.D. Associate Professor
Department of Computer Science Tel: (306) 585-4088
University of Regina Fax: (306) 585-4745
Regina, Saskatchewan E-mail: yxiang@cs.uregina.ca
Canada S4S 0A2 WWW: http://cs.uregina.ca/~yxiang/
>Anders L Madsen wrote:
>> Hi All,
>>
>> As has been mentioned by many researchers, a good way of exploiting
>> parallelisme in multiprocessor computers when performing Bayesian
>> inference is to have the table operations split up in independent
>> subtasks.
>>
>> Does anyone know of any algorithms developed for performing
>> multiplication, division, and marginalization of multiple dimensioned
>> probability potentials or more general multiple dimensioned structures?
>>
>> Any replies will be appreciated.