Out-of-distribution detection has become an important theme in machine learning (ML) field, since the recognition of unseen data either "similar" or not (in- or out-of-distribution) to the ones the ML system has been trained on may lead to potentially fatal conse- quences. Operational data compliance with the training data has to be verified by the data analyst, who must also understand, in operation, if the autonomous decision-making is still safe or not. In this paper, we study an out-of-distribution (OoD) detection approach based on a rule- based eXplainable Artificial Intelligence (XAI) model. Specifically, the method relies on an innovative metric, i.e., the weighted mutual infor- mation, able to capture the different way decision rules are used in case of in- and OoD data.
Weighted Mutual Information for Out-Of-Distribution Detection
Giacomo De Bernardi;Sara Narteni;Enrico Cambiaso;Marco Muselli;Maurizio Mongelli
2023
Abstract
Out-of-distribution detection has become an important theme in machine learning (ML) field, since the recognition of unseen data either "similar" or not (in- or out-of-distribution) to the ones the ML system has been trained on may lead to potentially fatal conse- quences. Operational data compliance with the training data has to be verified by the data analyst, who must also understand, in operation, if the autonomous decision-making is still safe or not. In this paper, we study an out-of-distribution (OoD) detection approach based on a rule- based eXplainable Artificial Intelligence (XAI) model. Specifically, the method relies on an innovative metric, i.e., the weighted mutual infor- mation, able to capture the different way decision rules are used in case of in- and OoD data.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.