165 citations · 165 across the 1 of their papers we have counts for
4 papers
Balancing the composition of word embeddings across heterogenous data sets
Stephanie Brandl, David Lassner, Maximilian Alber
Word embeddings capture semantic relationships based on contextual information and are the basis for a wide variety of natural language processing applications. Notably these relat…
Explanations can be manipulated and geometry is to blame
Ann-Kathrin Dombrowski, Maximilian Alber, Christopher J. Anders +3
Explanation methods aim to make neural networks more trustworthy and interpretable. In this paper, we demonstrate a property of explanation methods which is disconcerting for both…
Software and application patterns for explanation methods
Maximilian Alber
Deep neural networks successfully pervaded many applications domains and are increasingly used in critical decision processes. Understanding their workings is desirable or even req…
The (Un)reliability of saliency methods
Pieter-Jan Kindermans, Sara Hooker, Julius Adebayo +5
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 m…