deep-significance - Easy and Meaningful Statistical Significance Testing in the Age of Neural Networks

Autor: Ulmer, Dennis, Hardmeier, Christian, Frellsen, Jes
Rok vydání: 2022
Předmět:
Druh dokumentu: Working Paper
Popis: A lot of Machine Learning (ML) and Deep Learning (DL) research is of an empirical nature. Nevertheless, statistical significance testing (SST) is still not widely used. This endangers true progress, as seeming improvements over a baseline might be statistical flukes, leading follow-up research astray while wasting human and computational resources. Here, we provide an easy-to-use package containing different significance tests and utility functions specifically tailored towards research needs and usability.
Databáze: arXiv