Plos One

By MD Justine MacNeil. 2015

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations (2017, methodology): “…a pixel-by-pixel level of resolution, do not capture the idea of salience as well as superpixel-based LIME or other recently developed methods for explaining image predictions [Zeiler and Fergus, 2014; Sundararajan et al. , 2016; Montavon et al. , 2017; Bach et al. , 2015; Shrikumar et al. , 2016].”
Differentiable Physics and Stable Modes for Tool-Use and Manipulation Planning (2018, background): “A large body of animal behavior studies that aim at characterizing intelligence in animals focus on experiments related to physical reasoning in novel situations, such as tool use, means-end sequential object manipulation, an the anticipation of physical effects [Köhler, 1917; Wimpenny et al., 2009]”
Predicting backbone Cα angles and dihedrals from protein sequences by stacked sparse auto‐encoder deep neural network (2014, background): “Two different angles can also be used for representing protein backbones.”
Modeling mutual feedback between users and recommender systems (2015, methodology): “Keywords: analysis of algorithms, network dynamics, online dynamics S Online supplementary data available ht tp :// do”
Profex: a graphical user interface for the Rietveld refinement program BGMN (2015, methodology): “Successful application of Profex by independent users was demonstrated for example by Pujari-Palmer et al. (2015) and Bobrovs et al. (2015).”
Causal Learning and Explanation of Deep Neural Networks via Autoencoded Activations (2018, methodology): “For example, gradient– based methods of explanation such as layerwise relevance propagation (LRP) [Bach et al. , 2015] and Grad–CAM [Sel-varaju et al. , 2016] attempt to explain the output activation of a class C in terms of the input P activations, realized for a speciﬁc input P j .”