Visual Interpretation of Kernel‐Based Prediction Models

By Katja Hansen, David Baehrens, Timon Schroeter, Matthias Rupp , Klaus‐Robert Müller . 2011

58 citations recorded by the source corpus.

Subfields: Computational Theory and Mathematics, Materials Chemistry, Safety, Robustness & Interpretability

How researchers see this paper

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

In Computational Theory and Mathematics

In Materials Chemistry

In Safety, Robustness & Interpretability

Citations in the corpus

Methods for interpreting and understanding deep neural networks (2017, background): “In combination with deep nonlinear machine learning models, they have been able to extract new in-∗ sights from complex physical, chemical, or biological systems [20, 21, 49, 43, 54].”
Interpreting random forest classification models using a feature contribution method (2013, methodology): “A method for visual interpretation of kernel-based prediction models is described in [11].”
Evaluating the Visualization of What a Deep Neural Network Has Learned (2015, background): “Only recently, the transparency problem has been receiving more attention for general nonlinear estimators [13], [14], [15], [16].”
Layer-Wise Relevance Propagation for Deep Neural Network Architectures (2016, background): “Several works have been dedicated to the understanding of general non-linear estimators [4, 3, 12].”
Neural Encoding and Decoding with Deep Learning for Dynamic Natural Vision (2016, methodology): “This optimization included 2 steps, combining the visualization methods based on masking (Zhou et al. 2014; Li 2016) and gradient (Baehrens et al. 2010; Hansen et al. 2011; Simonyan et al. 2013; Springenberg et al. 2014).”
Ten simple rules for predictive modeling of individual differences in neuroimaging (2019, methodology): “To assess the interpretability of features from a complex model, there are methods that employ post-hoc analyses to vary aspects of the model and evaluate how these variations affect model performance (Baehrens et al., 2010; Hansen et al., 2011; Ribeiro et al., 2016).”
Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications (2021, background): “Transposing this concept of maximizing utility to the domain of explanation, quantifying the utility of the explanation would first require to define what is the ultimate target task (the explanation being only an intermediate step) and then assessing by how much the use of explanation by the human ”
Explaining machine learning models in sales predictions (2017, methodology): “The method was shown to be practically useful with a kernel-based classification method to predict molecular attributes (Hansen et al., 2011).”