Feature Selection Using a Multilayer Perceptron

By Dennis W. Ruck, Steven K. Rogers, Matthew Kabrisky, W. Afb. 1990

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

Opening black box Data Mining models using Sensitivity Analysis (2011, methodology): “While initially proposed for NN, SA can be used with virtually any supervised learning method, such as partial least squares [15] and SVM [16].”
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).”
Neural Networks and Deep Learning (2018, unknown): “This approach also has the useful property that it can be used for feature selection [406].”
Using sensitivity analysis and visualization techniques to open black box data mining models (2013, methodology): “Recent examples of successful applications of these black box methods are: network intrusion detection using NN [16], wine quality prediction using SVM [7] and text sentiment classification (e.g., positive/negative movie-review identification) using ensembles of SVM and other DM methods [34].”
Federated Learning on Non-IID Data: A Survey (2021, methodology): “Three types of neural network models, multi-layer perceptrons [109, 35], convolutional neural networks [74] and long-short-term-memory (LSTM) [52], are originally used in the FedAvg algorithm for image classification and next word prediction tasks.”
Comparison of machine learning and traditional classifiers in glaucoma diagnosis (2002, methodology): “the LEAPS [52] for LDA, saliency metric [53] for MLP and”
Designing fuzzy inference systems from data: An interpretability-oriented review (2001, background): “Neural networks may be helpful too: the output sensitivity to the input variables can be used to rank the input variables [48], [49].”
Deep learning based large scale handwritten Devanagari character recognition (2015, background): “But, performance of such a network has always been greatly dependent on the selection of good representing features[4][5].”