Interpretable Representations in Explainable AI: From Theory to Practice

arXiv:2008.07007v4 Announce Type: replace
Abstract: Interpretable representations are the backbone of many explainers that target black-box predictive systems based on artificial intelligence and machine learning algorithms. They translate the low-level data representation necessary for good predictive performance into high-level human-intelligible concepts used to convey the explanatory insights. Notably, the explanation type and its cognitive complexity are directly controlled by the interpretable representation, tweaking which allows to target a particular audience and use case. However, many explainers built upon interpretable representations …

abstract algorithms artificial artificial intelligence arxiv box concepts cs.ai cs.lg data explainable ai explainers good human insights intelligence low machine machine learning machine learning algorithms performance practice predictive representation stat.ml systems theory translate type