Analyzing Local Structure in Kernel-Based Learning: Explanation, Complexity, and Reliability Assessment

By Grgoire Montavon, Mikio L. Braun, Tammo Krueger, K. Müller. 2013

41 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

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

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Explaining nonlinear classification decisions with deep Taylor decomposition (2015, methodology): “Some methods seek to provide a global understanding of the trained model, by measuring important characteristics of it, such as the noise and relevant dimensionality of its feature space(s) [28, 29, 30], its invariance to certain”
Evaluating the Visualization of What a Deep Neural Network Has Learned (2015, background): “Note that this aspect differs from feature selection [12], where the question is: which features are on average salient for the ensemble of training data? Only recently, the transparency problem has been receiving more attention for general nonlinear estimators [13]–[16].”
A survey of machine learning for big data processing (2016, background): “Here, the original nonlinear problem can be transformed into a linear formulation in a higher dimensional space F with an appropriate kernel k [65]:”
Layer-Wise Relevance Propagation for Deep Neural Network Architectures (2016, background): “Recently several methods have been proposed for analyzing what a deep neural network has learned [9, 17, 18].”
Nonlinear gradient denoising: Finding accurate extrema from inaccurate functional derivatives (2015, unknown): “[27] G.”
On layer-wise representations in deep neural networks (2013, methodology): “Finally, Montavon et al. (2013a) have developed a local extension of dimensionality and noise estimates, which consists of performing the analysis on a local kernel defined as kξ(x, x′) = k(ξ, x) · k(x, x′) · k(x′, ξ).”