The last decade of machine learning has seen drastic increases in scale and capabilities.
Deep neural networks (DNNs) are increasingly being deployed in the real world. However …

Recently, a series of studies have tried to extract interactions between input variables
modeled by a DNN and define such interactions as concepts encoded by the DNN …

This paper introduces the system of game-theoretic interactions, which connects both the
explanation of knowledge encoded in a deep neural networks (DNN) and the explanation of …

Various attribution methods have been developed to explain deep neural networks (DNNs)
by inferring the attribution/importance/contribution score of each input variable to the final …

Various attribution methods have been developed to explain deep neural networks (DNNs)
by inferring the attribution/importance/contribution score of each input variable to the final …

This paper explains the generalization power of a deep neural network (DNN) from the
perspective of interactive concepts. Many recent studies have quantified a clear emergence …

Masking some input variables of a deep neural network (DNN) and computing output
changes on the masked input sample represent a typical way to compute attributions of input …

Deep neural networks (DNN) s have shown remarkable effectiveness in synthetic aperture
radar (SAR) target recognition. However, the explainability problem for DNNs remains …

The most common way to evaluate AI systems is by analyzing their performance on a test
set. However, test sets can fail to identify some problems (such as out-of-distribution failures) …

This paper proposes a metric to evaluate the objectiveness of explanation methods of neural
networks, ie, the accuracy of the estimated importance/attribution/saliency values of input …