18 dempster a , laird n , rubin d . maximum likelihood from incomplete data via the em algorithm 進(jìn)一步,數(shù)據(jù)降維的結(jié)果可通過與兩個空間相關(guān)度量的最大似然解得到。
In this paper , we present a theoretical analysis on the correct convergence of the em algorithm for gaussian mixtures 本文對高斯混合體em算法的正確收斂性問題進(jìn)行了理論研究。
However , there has been still an important but unsolved problem : whether the em algorithm can converge to the correct solution 然而, em算法能否收斂到正確解一直是一個困難的問題。