In this paper, we show how support vector machine (SVM) can be employed as a powerful tool for $k$-nearest neighbor (kNN) classifier. A novel multi-class dimensionality reduction approach, Discriminant Analysis via Support Vectors (SVDA), is in

Kernel Discriminant Analysis a kernel extension of Linear Discriminant Analysis technique which is a well-known feature extraction technique.-Kernel Discriminant Analysis is a kernel extension of Linear Discriminant Analysis technique which is a well

matlab论坛里找到的使用自己的数据进行实验，可用。KFDA里就是使用例程。里面是有5类数据。通过高斯核进行LDA分类。-by using the FDA with Gaussian kernel，to classify five different patterns。

This file was written by Bilwaj K. Gaonkar This is intended to provide an LDA implementation for high dimension low sample size data

经典kernel LDA算法，可用于人脸识别算法，很好用(Classic kernel LDA algorithm, can be used for face recognition algorithm, very good use)