Title :
Approximation of Bayes code for Markov sources
Author :
Takeuchi, Jun-ichi ; Kawabata, Tsutomu
Author_Institution :
NEC Corp., Kawasaki, Japan
Abstract :
We give an approximation formula for the predictive Bayes code for FSMX models (subspaces of Markov models). Moreover, we empirically show that the code using our approximation formula with the Jeffreys prior employed gives shorter code length than the one using the Laplace estimator for the first order Markov models
Keywords :
Bayes methods; Markov processes; approximation theory; finite state machines; prediction theory; source coding; FSMX models; Jeffreys prior; Markov sources; approximation formula; code length; first order Markov models; predictive Bayes code; Artificial intelligence; Minimax techniques; National electric code; Predictive models; Probability distribution;
Conference_Titel :
Information Theory, 1995. Proceedings., 1995 IEEE International Symposium on
Conference_Location :
Whistler, BC
Print_ISBN :
0-7803-2453-6
DOI :
10.1109/ISIT.1995.550378
