论文标题
深度显着性 - 神经网络时代的轻松而有意义的统计显着性测试
deep-significance - Easy and Meaningful Statistical Significance Testing in the Age of Neural Networks
论文作者
论文摘要
大量的机器学习（ML）和深度学习（DL）研究具有经验性质。然而，统计显着性测试（SST）仍未被广泛使用。这危害了真正的进步，因为对基线的改进可能是统计漏斗，在浪费人类和计算资源的同时，导致后续研究误入歧途。在这里，我们提供了一个易于使用的软件包，其中包含针对研究需求和可用性的不同意义测试和实用程序功能。
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.
