Deep learning describes a class of machine learning algorithms that are capable of
combining raw inputs into layers of intermediate features. These algorithms have recently …

Deep neural networks (DNNs) are an indispensable machine learning tool despite the
difficulty of diagnosing what aspects of a model's input drive its decisions. In countless real …

To have a better understanding and usage of Convolution Neural Networks (CNNs), the
visualization and interpretation of CNNs has attracted increasing attention in recent years. In …

Recent developments in machine learning have introduced models that approach human
performance at the cost of increased architectural complexity. Efforts to make the rationales …

Understanding the flow of information in Deep Neural Networks (DNNs) is a challenging
problem that has gain increasing attention over the last few years. While several methods …

We introduce instancewise feature selection as a methodology for model interpretation. Our
method is based on learning a function to extract a subset of features that are most …

Saliency methods aim to explain the predictions of deep neural networks. These methods
lack reliability when the explanation is sensitive to factors that do not contribute to the model …

Saliency methods are used extensively to highlight the importance of input features in model
predictions. These methods are mostly used in vision and language tasks, and their …

We investigate whether post-hoc model explanations are effective for diagnosing model
errors--model debugging. In response to the challenge of explaining a model's prediction, a …

The purported “black box” nature of neural networks is a barrier to adoption in applications
where interpretability is essential. Here we present DeepLIFT (Deep Learning Important …