High information redundancy and correlation in face images result in efficiencies when such images are used directly for recognition. In this paper, discrete cosine transforms are used to reduce image information redundancy because only a subset of t

利用BP神经网络对邮件分类，2分类，实现反向传播算法细节，非直接函数调用(BP neural network is used to classify mail, 2 classifications, to implement the details of backpropagation algorithm, non direct function call.)