模式识别的最大熵方法
MAXIMUM ENTROPY METHOD FOR PATTERN RECOGNITION
-
摘要: 本文提出了模式识别的最大熵方法,其基本思想是求出最大熵概率分布,再求出条件概率分布,进而作出二值分类.它的特点是能最大限度的利用已有信息作出最合理的推测.和其它方法相比较,该方法的突出优点是在小样本情况下仍能保持很好的识别率.Abstract: In this paper, maximum entropy method is applied to pattern recognition; the key point is to find the probability distribution that has maximum entropy measure, which ensures that the distribution is most reasonable.Compared with other methods, this method is especially useful when the sample set is small.