16 Mar linear discriminator
Linear discriminator functions are used to classify data. Linear Discriminant Analysis (LDA) is most commonly used to reduce the complexity of multi-dimensional data sets by focusing on principal attributes, features or variables and filtering out less important characteristics. This work may be the main classifier, or a pre-processing step for pattern-classification and machine learning applications. One outcome is to overlay a dataset onto a simplified space to improve the separation of objects in each class and avoid overfitting. This may also reduce computational costs.