Data Selection for Neural Networks

Mirosław Kordos

Several approaches to joined feature and instance selection in neural
network leaning are discussed and experimentally evaluated in respect to classification
accuracy and dataset compression, considering also their computational
complexity. These include various versions of feature and instance selection
prior to the network learning, the selection embedded in the neural network and
hybrid approaches, including solutions developed by us. The advantages and
disadvantages of each approach are discussed and some possible improvements
are proposed.
Słowa kluczowe: Neural Networks, Data Selection, Feature Selection, Instance Selection

[1] Kordos M., Blachnik M., Bialka S., Instance selection in logical rule extraction
for regression problems. Lecture Notes in Artificial Intelligence, 2013, 7895, pp.
[2] Blachnik M., Kordos M., Simplifying SVM with weighted LVQ algorithm. Lecture
Notes in Computer Science, 2011, 6936, pp. 212–219.
[3] Liu H., Computational Methods of Feature Selection. Chapman and Hall, 2007.
[4] Stanczyk U., Jain L.C., Feature Selection for Data and Pattern Recognition.
Springer, 2015.
[5] Uribe C., Isaza C., Expert knowledge-guided feature selection for data-based industrial
process monitoring. Rev. Fac. Ing. Univ. Antioquia, 2012, 65, pp. 112–
[6] Kordos M., Cwiok A., A new approach to neural network based stock trading
strategy. Lecture Notes in Computer Science, 2011, 6936, pp. 429–436.
[7] Hofmann M., Klinkenberg R., RapidMiner: Data Mining Use Cases and Business
Analytics Applications. Chapman and Hall/CRC, 2016.
[8] Sun X., Chan P.K., An analysis of instance selection for neural networks to
improve training speed. International Conference on Machine Learning and Applications,
2014, pp. 288–293.
[9] Garcia S., Derrac J., Cano J.R., Herrera F., Prototype selection for nearest neighbor
classification: Taxonomy and empirical study. IEEE Transactions on Pattern
Analysis and Machine Intelligence, 2012, 34, pp. 417–435.
[10] Olvera-Lapez J.A., Carrasco-Ochoa J.A., Martin J.F., Kittler J., A review of
instance selection methods. Artificial Intelligence Review, 2010, 34, pp. 133–143.
[11] Grochowski M., Jankowski N., Comparison of instance selection algorithms. Lecture
Notes in Computer Science, 2004, 3070, pp. 580–585.
[12] Antonelli M., Ducange P., Marcelloni F., Genetic training instance selection
in multiobjective evolutionary fuzzy systems: A coevolutionary approach. IEEE
Transactions on Fuzzy Systems, 2012, 20, pp. 276–290.
[13] Anwar I.M., Salama K.M., Abdelbar A.F., Instance selection with ant colony
optimization. Procedia Computer Science, 2015, 53, pp. 248–256.
[14] Derrac J., Cornelis C., Garcia S., Herrera F., Enhancing evolutionary instance
selection algorithms by means of fuzzy rough set based feature selection. Information
Sciences, 2012, 186 (73–92).
[15] Wilson D.R., Martinez T.R., Reduction techniques for instance-based learning
algorithms. Machine Learning, 2000, 38, pp. 257–286.
[16] Blachnik M., Kordos M., Bagging of instance selection algorithms. Lecture Notes
in Computer Science, 2014, 8468, pp. 40–51.
[17] Kordos M., Instance selection optimization for neural network training. Lecture
Notes in Artificial Intelligence, 2016, 9692, pp. 610–620.
[18] Tsaia C.F., Eberleb W., Chu C.Y., Genetic algorithms in feature and instance
selection. Knowledge-Based Systems, 2013, 39, pp. 240–247.
[19] Leray P., Gallinari P., Feature selection with neural networks. Behaviormetrika,
1999, 26, pp. 145–166.
[20] Rusiecki A., Kordos M., Kaminski T., Gren K., Training neural networks on
noisy data. Lecture Notes in Artificial Intelligence, 2014, 8467, pp. 131–142.
[21] Alcala-Fdez J., et al., Keel data-mining software tool: Data set repository,
integration of algorithms and experimental analysis framework., Journal of Multiple-Valued Logic and Soft
Computing, 2011, 17, pp. 255–287.

Czasopismo ukazuje się w sposób ciągły on-line.
Pierwotną formą czasopisma jest wersja elektroniczna.

Wersja papierowa czasopisma dostępna na