Linear Discriminant Analysis for Two Classes via Recursive Neural Network Reduction of the Class Separation
نویسنده
چکیده
A method for the linear discrimination of two classes is presented. It maximizes the Patrick-Fisher (PF) distance between the projected class-conditional densities. Since the PF distance is a highly nonlinear function, we propose a method, which searches for the directions corresponding to several large local maxima of the PF distance. Its novelty lies in a neural network transformation of the data along a found direction into data with deflated maxima of the PF distance and iteration to obtain the next direction. A simulation study indicates that the method has the potential to find the global maximum of the PF distance.
منابع مشابه
Maxi-Min discriminant analysis via online learning
Linear Discriminant Analysis (LDA) is an important dimensionality reduction algorithm, but its performance is usually limited on multi-class data. Such limitation is incurred by the fact that LDA actually maximizes the average divergence among classes, whereby similar classes with smaller divergence tend to be merged in the subspace. To address this problem, we propose a novel dimensionality re...
متن کاملEnhancing Efficiency of Neural Network Model in Prediction of Firms Financial Crisis Using Input Space Dimension Reduction Techniques
The main focus in this study is on data pre-processing, reduction in number of inputs or input space size reduction the purpose of which is the justified generalization of data set in smaller dimensions without losing the most significant data. In case the input space is large, the most important input variables can be identified from which insignificant variables are eliminated, or a variable ...
متن کاملECE662: Pattern Recognition and Decision Making Processes: HW TWO
In this report experiments are carried out to evaluate some of the techniques that we have covered in the ECE662 course material. In particular in the first exercise a numerical experiment is carried out to test effect of applying a Fischer linear discriminant approach to linearly separable data. An extra step is also take to test the effect of the technique on non-linearly separable data. In t...
متن کاملTwo-class pattern discrimination via recursive optimization of Patrick-Fisher distance
A method for the linear discrimination of two classes is presented. It searches for the discriminant direction which maximizes the Patrick-Fisher (PF) distance between the projected class-conditional densities. It is a nonparametric method, in the sense that the densities are estimated from the data. Since the PF distance is a highly nonlinear function, we propose a recursive optimization proce...
متن کاملImproving Chernoff criterion for classification by using the filled function
Linear discriminant analysis is a well-known matrix-based dimensionality reduction method. It is a supervised feature extraction method used in two-class classification problems. However, it is incapable of dealing with data in which classes have unequal covariance matrices. Taking this issue, the Chernoff distance is an appropriate criterion to measure distances between distributions. In the p...
متن کامل