Next meeting: 2pm Wednesday 23 Feb, in Coombs seminar room E, to discuss:
Abstract:
This paper discusses partial belief updates and simultaneous belief updates. Contrary to what many probabilists think, it is shown here that belief updates can be modeled by using Jeffrey conditionalization (JC) and that the modeling results so obtained are similar to those obtained by using Maximal Entropy Principle. With the help of these results, it is argued that Kullback-Leibler distance measure in Maximal Entropy Principle is more plausible than other distance measures.
This paper discusses partial belief updates and simultaneous belief updates. Contrary to what many probabilists think, it is shown here that belief updates can be modeled by using Jeffrey conditionalization (JC) and that the modeling results so obtained are similar to those obtained by using Maximal Entropy Principle. With the help of these results, it is argued that Kullback-Leibler distance measure in Maximal Entropy Principle is more plausible than other distance measures.
No comments:
Post a Comment