We study the understanding of deep neural networks from the scope in which they are trained on. While the accuracy of these models is usually impressive on the aggregate level, they still make mistakes, sometimes on cases that appear to be trivial. Moreover, these models are not reliable in realizing what they do not know leading to failures such as adversarial vulnerability and out-of-distribution failures. Here, we propose a measure for quantifying the ambiguity of inputs for any given model with regard to the scope of its training. We define the ambiguity based on the geometric arrangements of the decision boundaries and the convex hull of training set in the feature space learned by the trained model, and demonstrate that a single ambiguity measure may detect a considerable portion of mistakes of a model on in-distribution samples, adversarial inputs, as well as out-of-distribution inputs. Using our ambiguity measure, a model may abstain from classification when it encounters ambiguous inputs leading to a better model accuracy not just on a given testing set, but on the inputs it may encounter at the world at large. In pursuit of this measure, we develop a theoretical framework that can identify the unknowns of the model in relation to its scope. We put this in perspective with the confidence of the model and develop formulations to identify the regions of the domain which are unknown to the model, yet the model is guaranteed to have high confidence.

翻译：暂无翻译