TY - CONF
T1 - deep-significance - Easy and Meaningful Statistical Significance Testing in the Age of Neural Networks
AU - Ulmer, Dennis Thomas
AU - Hardmeier, Christian
AU - Frellsen, Jes
PY - 2022/4/29
Y1 - 2022/4/29
N2 - 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.
AB - 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.
KW - Machine Learning
KW - Deep Learning
KW - Statistical Significance Testing
KW - Empirical Research
KW - Computational Resources
KW - Machine Learning
KW - Deep Learning
KW - Statistical Significance Testing
KW - Empirical Research
KW - Computational Resources
UR - https://arxiv.org/pdf/2204.06815.pdf
M3 - Paper
ER -