{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T21:54:00Z","timestamp":1776722040382,"version":"3.51.2"},"reference-count":34,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2018,4,3]],"date-time":"2018-04-03T00:00:00Z","timestamp":1522713600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>Artificial neural networks are currently one of the most commonly used classifiers and over the recent years they have been successfully used in many practical applications, including banking and finance, health and medicine, engineering and manufacturing. A large number of error functions have been proposed in the literature to achieve a better predictive power. However, only a few works employ Tsallis statistics, although the method itself has been successfully applied in other machine learning techniques. This paper undertakes the effort to examine the \r\n          \r\n            \r\n              q\r\n            \r\n          \r\n        -generalized function based on Tsallis statistics as an alternative error measure in neural networks. In order to validate different performance aspects of the proposed function and to enable identification of its strengths and weaknesses the extensive simulation was prepared based on the artificial benchmarking dataset. The results indicate that Tsallis entropy error function can be successfully introduced in the neural networks yielding satisfactory results and handling with class imbalance, noise in data or use of non-informative predictors.<\/jats:p>","DOI":"10.3390\/e20040249","type":"journal-article","created":{"date-parts":[[2018,4,3]],"date-time":"2018-04-03T13:31:51Z","timestamp":1522762311000},"page":"249","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Simulation Study on the Application of the Generalized Entropy Concept in Artificial Neural Networks"],"prefix":"10.3390","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6953-8907","authenticated-orcid":false,"given":"Krzysztof","family":"Gajowniczek","sequence":"first","affiliation":[{"name":"Department of Informatics, Faculty of Applied Informatics and Mathematics, Warsaw University of Life Sciences-SGGW, Nowoursynowska 159, 02-787 Warsaw, Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arkadiusz","family":"Or\u0142owski","sequence":"additional","affiliation":[{"name":"Department of Informatics, Faculty of Applied Informatics and Mathematics, Warsaw University of Life Sciences-SGGW, Nowoursynowska 159, 02-787 Warsaw, Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomasz","family":"Z\u0105bkowski","sequence":"additional","affiliation":[{"name":"Department of Informatics, Faculty of Applied Informatics and Mathematics, Warsaw University of Life Sciences-SGGW, Nowoursynowska 159, 02-787 Warsaw, Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2018,4,3]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1016\/j.eswa.2007.10.005","article-title":"Neural networks and statistical techniques: A review of applications","volume":"36","author":"Paliwal","year":"2009","journal-title":"Expert Syst. Appl."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Bishop, C.M. (1995). Neural Networks for Pattern Recognition, Oxford University Press.","DOI":"10.1093\/oso\/9780198538493.001.0001"},{"key":"ref_3","first-page":"133","article-title":"Prediction improvement via smooth component analysis and neural network mixing","volume":"Volume 4132","author":"Kollias","year":"2006","journal-title":"Theoretical Computer Science and General Issues"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"223","DOI":"10.3233\/IFS-151748","article-title":"Short term electricity forecasting based on user behavior using individual smart meter data","volume":"30","author":"Gajowniczek","year":"2015","journal-title":"Intell. Fuzzy Syst."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"6879","DOI":"10.1016\/j.eswa.2012.01.008","article-title":"Insolvency modeling in the cellular telecommunication industry","volume":"39","author":"Szczesny","year":"2012","journal-title":"Expert Syst. Appl."},{"key":"ref_6","unstructured":"Kalman, B.L., and Kwasny, S.C. (1991, January 18\u201321). A Superior Error Function for Training Neural Networks. Proceedings of the IEEE International Joint Conference on Neural Networks, Singapore."},{"key":"ref_7","unstructured":"White, H. (1992). Artificial Neural Networks: Approximation and Learning Theory, Blackwell Publishing."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Golik, P., Doetsch, P., and Ney, H. (2013, January 25\u201329). Cross-entropy vs squared error training: A theoretical and experimental comparison. Proceedings of the 14th Annual Conference of the International Speech Communication Association \u201cInterspeech-2013\u201d, Lyon, France.","DOI":"10.21437\/Interspeech.2013-436"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Hastie, T.J., Tibshirani, R.J., and Friedman, J.H. (2009). The Elements of Statistical Learning: Data Mining, Inference, and Prediction, Springer.","DOI":"10.1007\/978-0-387-84858-7"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Waghmare, L.M., Bidwai, N.N., and Bhogle, P.P. (2007, January 5\u20138). Neural network weight initialization. Proceedings of the IEEE International Conference on Mechatronics and Automation, Harbin, China.","DOI":"10.1109\/ICMA.2007.4303625"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Ramos, E.Z., Nakakuni, M., and Yfantis, E. (2017, January 9\u201311). Quantitative measures to evaluate neural network weight initialization strategies. Proceedings of the IEEE Computing and Communication Workshop and Conference (CCWC), Las Vegas, NV, USA.","DOI":"10.1109\/CCWC.2017.7868389"},{"key":"ref_12","unstructured":"Falas, T., and Stafylopatis, A.G. (1999, January 10\u201316). The impact of the error function selection in neural network-based classifiers. Proceedings of the International Joint Conference on Neural Networks, Washington, DC, USA."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"297","DOI":"10.1080\/00207160108805026","article-title":"An improved error signal for the backpropagation model for classification problems","volume":"76","author":"Shamsuddin","year":"2001","journal-title":"Int. J. Comput. Math."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1016\/S0020-0255(96)00200-9","article-title":"The generalized sigmoid activation function: Competitive supervised learning","volume":"99","author":"Narayan","year":"1997","journal-title":"Inf. Sci."},{"key":"ref_15","unstructured":"Kamruzzaman, J., and Aziz, S.M. (2002, January 12\u201317). A note on activation function in multilayer feedforward learning. Proceedings of the 2002 International Joint Conference on Neural Networks IJCNN\u201902, Honolulu, HI, USA."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Bourlard, H.A., and Morgan, N. (1993). Connectionist Speech Recognition: A Hybrid Approach, Kluwer Academic Publishers.","DOI":"10.1007\/978-1-4615-3210-1"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"310","DOI":"10.1007\/s00521-005-0467-y","article-title":"Revisiting squared-error and cross-entropy functions for training neural network classifiers","volume":"14","author":"Kline","year":"2005","journal-title":"Neural Comput. Appl."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"468","DOI":"10.1590\/S0103-97332009000400023","article-title":"Q-distributions in complex systems: A brief review","volume":"39","author":"Picoli","year":"2009","journal-title":"Braz. J. Phys."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"383","DOI":"10.1109\/TNNLS.2015.2513365","article-title":"QRNN: Q-generalized random neural network","volume":"28","author":"Stosic","year":"2016","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"779","DOI":"10.1016\/j.neunet.2011.03.014","article-title":"Evolutionary q-Gaussian radial basis function neural networks for multiclassification","volume":"24","year":"2011","journal-title":"Neural Netw."},{"key":"ref_21","first-page":"127","article-title":"Use of the q-Gaussian function in radial basis function networks","volume":"Volume 5","author":"Abraham","year":"2009","journal-title":"Foundations of Computational Intelligence"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1186\/s13040-017-0154-4","article-title":"PMLB: A Large Benchmark Suite for Machine Learning Evaluation and Comparison","volume":"10","author":"Olson","year":"2017","journal-title":"BioData Min."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"623","DOI":"10.1002\/j.1538-7305.1948.tb00917.x","article-title":"A Mathematical Theory of Communication","volume":"27","author":"Shannon","year":"1948","journal-title":"Bell Syst. Tech. J."},{"key":"ref_24","unstructured":"Tsallis, C. (2009). Introduction to Nonextensive Statistical Mechanics, Springer."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Cover, T.M., and Thomas, J.A. (2006). Elements of Information Theory, Wiley Publishing.","DOI":"10.1002\/047174882X"},{"key":"ref_26","unstructured":"Fritsch, S., and Guenther, F. (2018, January 10). Neuralnet: Training of Neural Networks. R Package Version 1.33. Available online: https:\/\/CRAN.R-project.org\/package=neuralnet."},{"key":"ref_27","unstructured":"Riedmiller, M. (1994). Rprop-Description and Implementation Details, University of Karlsruhe. Technical Report."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1016\/j.neucom.2004.11.016","article-title":"New globally convergent training scheme based on the resilient propagation algorithm","volume":"64","author":"Anastasiadis","year":"2005","journal-title":"Neurocomputing"},{"key":"ref_29","first-page":"128","article-title":"Generalized Entropy Cost Function in Neural Networks","volume":"Volume 10614","author":"Lintas","year":"2017","journal-title":"Artificial Neural Networks and Machine Learning"},{"key":"ref_30","unstructured":"Kuhn, M., Wing, J., Weston, S., Williams, A., Keefer, C., Engelhardt, A., Cooper, T., Mayer, Z., Kenkel, B., and The R Core Team (2018, January 10). Caret: Classification and Regression Training. R package Version 6.0-76. Available online: https:\/\/CRAN.R-project.org\/package=caret."},{"key":"ref_31","first-page":"39","article-title":"Comparison of Decision Trees with Renyi and Tsallis Entropy Applied for Imbalanced Churn Dataset","volume":"5","author":"Gajowniczek","year":"2015","journal-title":"Ann. Comput. Sci. Inf. Syst."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1002\/1097-0142(1950)3:1<32::AID-CNCR2820030106>3.0.CO;2-3","article-title":"An index for rating diagnostic tests","volume":"3","author":"Youden","year":"1950","journal-title":"Cancer"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"38","DOI":"10.12693\/APhysPolA.127.A-38","article-title":"Q-entropy approach to selecting high income households","volume":"127","author":"Gajowniczek","year":"2015","journal-title":"Acta Phys. Pol. A"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"971","DOI":"10.12693\/APhysPolA.129.971","article-title":"Entropy Based Trees to Support Decision Making for Customer Churn Management","volume":"129","author":"Gajowniczek","year":"2016","journal-title":"Acta Phys. Pol. A"}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/20\/4\/249\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T14:59:31Z","timestamp":1760194771000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/20\/4\/249"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4,3]]},"references-count":34,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2018,4]]}},"alternative-id":["e20040249"],"URL":"https:\/\/doi.org\/10.3390\/e20040249","relation":{},"ISSN":["1099-4300"],"issn-type":[{"value":"1099-4300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,4,3]]}}}