Finite memory multiple hypothesis testing: Close-to-optimal schemes for Bernoulli problems
暂无分享,去创建一个
The design of optimal, time-invariant, randomized, finite-state automata for K -hypothesis testing is an open problem for K > 2 . A lower bound is constructed on the smallest probability of error achievable by m -state automata solving a three-hypothesis Bernoulli problem. A class of close-to-optimal automata is exhibited that requires at most one extra bit of memory to match the performnnce of an optimal automaton.
[1] T. Cover,et al. Learning with Finite Memory , 1970 .
[2] Daniel Sagalowicz. Hypothesis testing with finite memory , 1970 .
[3] Martin E. Hellman,et al. The effects of randomization on finite-memory decision schemes , 1972, IEEE Trans. Inf. Theory.
[4] Francisco J. Samaniego,et al. Estimating a binomial parameter with finite memory , 1973, IEEE Trans. Inf. Theory.
[5] S. Yakowitz. Multiple Hypothesis Testing by Finite Memory Algorithms , 1974 .