Generative and reproducible benchmarks for comprehensive evaluation of machine learning classifiers.
Generative and reproducible benchmarks for comprehensive evaluation of machine learning classifiers.
复制标题
DOI:
10.1126/sciadv.abl4747
复制
发表时间:
2022-11-25
期刊:
影响因子:
13.6
通讯作者:
中科院分区:
文献类型:
--
作者:
Understanding the strengths and weaknesses of machine learning (ML) algorithms is crucial to determine their scope of application. Here, we introduce the Diverse and Generative ML Benchmark (DIGEN), a collection of synthetic datasets for comprehensive, reproducible, and interpretable benchmarking of ML algorithms for classification of binary outcomes. The DIGEN resource consists of 40 mathematical functions that map continuous features to binary targets for creating synthetic datasets. These 40 functions were found using a heuristic algorithm designed to maximize the diversity of performance among multiple popular ML algorithms, thus providing a useful test suite for evaluating and comparing new methods. Access to the generative functions facilitates understanding of why a method performs poorly compared to other algorithms, thus providing ideas for improvement. Introducing DIGEN benchmark—a collection of synthetic datasets for classification of binary outcomes.
登录
查看更多内容
影响因子:
4.5
作者:
Olson RS;La Cava W;Orzechowski P;Urbanowicz RJ;Moore JH
通讯作者:
Moore JH
影响因子:
2.2
作者:
KOZA, JR
通讯作者:
KOZA, JR
影响因子:
4.5
作者:
Friedman, JH
通讯作者:
Friedman, JH
影响因子:
13.6
作者:
Udrescu, Silviu-Marian;Tegmark, Max
通讯作者:
Tegmark, Max
影响因子:
14.3
作者:
Deb, Kalyanmoy;Jain, Himanshu
通讯作者:
Jain, Himanshu