Feature selection with neural networks

By Antanas Verikas, Marija Bacauskiene. Pattern Recognition Letters, 2002

356 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/bb1f3c8c5489fa21a1f88ea78c6832ce18ab9df0

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

Hybrid and ensemble-based soft computing techniques in bankruptcy prediction: a survey (2010, background): “A large variety of feature selection techniques that result in a suboptimal feature subset have been proposed (Kudo and Sklansky 2000; Verikas and Bacauskiene 2002).”
A neural network approach using multi-scale textural metrics from very high-resolution panchromatic imagery for urban land-use classification (2009, background): “Intuitively, any classification approach should include only those features that make significant contributions, which should result in better performance ( Verikas & Bacauskiene, 2002 ).”
SAM: Structural Agnostic Model, Causal Discovery and Penalized Adversarial Learning (2018, background): “Therefore, SAM borrows inspiration from sparse feature selection methods (Leray and Gallinari, 1999), and conditional adversarial training (Goodfellow et al., 2014; Mirza and Osindero, 2014).”
Artificial neural networks in medical diagnosis (2013, methodology): “The most important and best-known tools for variable selection are powerful mathematical means of data mining such as principal components analysis, genetic algorithm (Yan et al. 2008), or ANNs (Verikas and Bacauskiene 2002).”
Data Mining for Molecules with 2-D Neural Network Sensitivity Analysis (2003, background): “…best subset of p features does not alwayscontainthebestsubsetofqfeatures,whereq < p); (iii) The best subset of features is often model dependent (Leray and Gallinari 1998); (iv) Some features are only relevant when another feature set is selected in combination; and, (v) A feature set may…”
Genetic programming for simultaneous feature selection and classifier design (2006, methodology): “Some neural network based FS schemes are discussed in [20], [21], and [22].”
Variable Selection Using SVM-based Criteria (2003, methodology): “Furthermore, similarly to neural-networks based variable selection (Leray and Gallinari, 1999), two approaches can be proposed for each criterion: • Zero-order method: in this case, the criterion C t is directly used for variable ranking, and the methods consists in identifying the variable that…”
Does Feature Selection Improve Classification? A Large Scale Experiment in OpenML (2016, background): “Multilayer Perceptrons are also supposed to learn themselves which features are relevant [21], however Figure 2(b) shows that in many cases feature selection makes a substantial difference for the better.”
Mining data with random forests: A survey and results of new tests (2011, background): “Previous tests of various variable selection techniques on this data set have shown that correct identification of all the noise variables is not an easy task [108,109].”