Szczegóły publikacji
Opis bibliograficzny
Generative and reproducible benchmarks for comprehensive evaluation of machine learning classifiers / Patryk ORZECHOWSKI, Jason H. Moore // Science Advances ; ISSN 2375-2548. — 2022 — vol. 8 no. 47 art. no. eabl4747, s. 1-5. — Bibliogr. s. 4-5, Abstr. — Publikacja dostępna online od: 2022-11-23. — P. Orzechowski - dod. afiliacja: University of Pennsylvania, USA
Autorzy (2)
- AGHOrzechowski Patryk
- Moore Jason H.
Dane bibliometryczne
| ID BaDAP | 144277 |
|---|---|
| Data dodania do BaDAP | 2023-01-03 |
| Tekst źródłowy | URL |
| DOI | 10.1126/sciadv.abl4747 |
| Rok publikacji | 2022 |
| Typ publikacji | artykuł w czasopiśmie |
| Otwarty dostęp |  |
| Creative Commons | |
| Czasopismo/seria | Science Advances |
Abstract
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.
