Sensitivity analysis for minimization of input data dimension for feedforward neural network

By J. Zurada, A. Malinowski, Ian Cloete. 1994

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

Methods for interpreting and understanding deep neural networks (2017, background): “A first approach to identify the most important input features is sensitivity analysis [77,66,29].”
Data Mining for Molecules with 2-D Neural Network Sensitivity Analysis (2003, methodology): “The second category for feature selection is based on evaluating the saliency of the features by monitoring variations in the output due to disturbances in the inputs (i.e., the descriptive features) (Ruck et al. 1990; Tarr 1991; Zurada et al. 1994).”
Deep convolutional neural networks for interpretable analysis of EEG sleep stage scoring (2017, methodology): “In the current study, we resort to sensitivity analysis [23, 24, 25] as a visualisation tool to better understand the decisions made by our network.”
Visualization of Nonlinear Classification Models in Neuroimaging - Signed Sensitivity Maps (2012, methodology): “The sensitivity analysis that we investigate for model interpretation is based on early work in (Zurada et al., 1994; Zurada et al., 1997).”
Applications of artificial neural networks for patterning and predicting aquatic insect species richness in running waters (2003, methodology): “There are many ways to perform the sensitivity analysis (Helton, 1993; Zurada et al., 1994; Hamby, 1994; Yao et al., 1998).”
Review and comparison of methods to study the contribution of variables in artificial neural network models (2003, methodology): “Nevertheless, in most works, these methods are used to eliminate irrelevant input, and are, therefore, called pruning methods (Guo and Uhrig, 1992; Zurada et al., 1994; El-Keib and Ma, 1995; Engelbrecht et al., 1995; Hsu et al., 1995; Maier et al., 1998; Yao et al., 1998; van Wijk and Bouten, 1999”
Logistic regression and artificial neural network classification models: a methodology review (2002, unknown): “Instead, one can use automatic relevance determination [9] or sensitivity analysis [17] to heuristically assess the importance of input variables for the classification result.”
Visualization of nonlinear kernel models in neuroimaging by sensitivity maps (2011, unknown): “two classes, hence t ∈ {−1, 1}, all expression may be generalized to multiple classes (Zurada et al., 1994).”