Class Mean Vectors, Self Monitoring and Self Learning for Neural Classifiers

Class Mean Vector s, Self - Monitoring and Self learning f or Neural Classifiers Eugene Wong University of California at Berkeley Abstract In this paper we explore the role of sample mean in building a neural network for classification . This role is surprisingly extensive and includes: direct computation of weights without training, performance monitoring for samples without known classification, and self - training for unlabeled data. Experimental c omputation o n a CIFAR - 10 data set provides promising empirical evidence on the ef ficacy of a simple and widely applicable approach to some difficult problems. Introduction We define a one layer K - class neural classifier as follows: For 1, 2, … . Classification is achieved by choosing the clas s with the maximum probability.