Event Selection Using an Extended Fisher Discriminant Method

2003/10/29 by Byron P. Roe, Roe, Byron P. · 1 citation
Computer Science · Engineering · Physics and Astronomy · #Data Analysis #Evolutionary Algorithms and Applications #FOS: Physical sciences #Fault Detection and Control Systems #Neural Networks and Applications #Statistics and Probability (physics.data-an) #physics.data-an

paper · pdf · doi:10.48550/arxiv.physics/0310145

Paper submitted to Stanford PHYSTAT 2003 conference, 3pages 2 figures

arxiv created 2003/10/29 · openalex publication_date 2003/10/29 · arxiv updated 2009/12/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

This note discusses the problem of choosing between hypotheses in a situation with many, correlated non-normal variables. A new method is introduced to shrink the many variables into a smaller subset of variables with zero mean, unit variance, and zero correlation coefficient between variables. These new variables are well suited to use in a neural net.

Cited by

• Study of accelerator neutrino interactions in a liquid argon TPC

Related

• An Extension of Fisher's Criterion: Theoretical Results with a Neural Network Realization
• Fisher's Pioneering work on Discriminant Analysis and its Impact on AI
• Variable Selection with Rigorous Uncertainty Quantification using Deep Bayesian Neural Networks: Posterior Concentration and Bernstein-von Mises Phenomenon
• ENNS: Variable Selection, Regression, Classification and Deep Neural Network for High-Dimensional Data
• Inferring independent sets of Gaussian variables after thresholding correlations