Py-CIU: A Python Library for Explaining Machine Learning Predictions Using Contextual Importance and Utility

Sule Anjomshoae, Timotheus Kampik, Kary Främling

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussaConference contributionScientific

Abstrakti

In this paper, we present the Py-CIU library, a generic Python tool for applying the Contextual Importance and Utility (CIU) explainable machine learning method. CIU uses concepts from decision theory to explain a machine learning model’s prediction specific to a given data point by investigating the importance and usefulness of individual features (or feature combinations) to a prediction. The explanations aim to be intelligible to machine learning experts as well as non-technical users. The library can be applied to any black-box model that outputs a prediction value for all classes
AlkuperäiskieliEnglanti
OtsikkoIJCAI-PRICAI 2020 Workshop on Explainable Artificial Intelligence (XAI)
TilaJulkaistu - 2020
OKM-julkaisutyyppiB3 Ei-soviteltu artikkeli konferenssin julkaisusarjassa
TapahtumaWorkshop on Explainable Artificial Intelligence - Virtual, Online, Yokohama, Japani
Kesto: 8 tammik. 20218 tammik. 2021

Workshop

WorkshopWorkshop on Explainable Artificial Intelligence
Maa/AlueJapani
KaupunkiYokohama
Ajanjakso08/01/202108/01/2021

Sormenjälki

Sukella tutkimusaiheisiin 'Py-CIU: A Python Library for Explaining Machine Learning Predictions Using Contextual Importance and Utility'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

Siteeraa tätä