{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T11:59:13Z","timestamp":1710244753899},"reference-count":21,"publisher":"University of Zielona G\u00f3ra, Poland","issue":"3","license":[{"start":{"date-parts":[[2019,9,1]],"date-time":"2019-09-01T00:00:00Z","timestamp":1567296000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,9,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>The learning of neural networks is becoming more and more important. Researchers have constructed dozens of learning algorithms, but it is still necessary to develop faster, more flexible, or more accurate learning algorithms. With fast learning we can examine more learning scenarios for a given problem, especially in the case of meta-learning. In this article we focus on the construction of a much faster learning algorithm and its modifications, especially for nonlinear versions of neural networks. The main idea of this algorithm lies in the usage of fast approximation of the Moore\u2013Penrose pseudo-inverse matrix. The complexity of the original singular value decomposition algorithm is <jats:italic>O<\/jats:italic>(<jats:italic>mn<\/jats:italic>2). We consider algorithms with a complexity of <jats:italic>O<\/jats:italic>(<jats:italic>mnl<\/jats:italic>),where <jats:italic>l&lt;n<\/jats:italic> and <jats:italic>l<\/jats:italic> is often significantly smaller than <jats:italic>n<\/jats:italic>. Such learning algorithms can be applied to the learning of radial basis function networks, extreme learning machines or deep ELMs, principal component analysis or even missing data imputation.<\/jats:p>","DOI":"10.2478\/amcs-2019-0043","type":"journal-article","created":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T02:53:24Z","timestamp":1569898404000},"page":"581-594","source":"Crossref","is-referenced-by-count":2,"title":["A Fast Neural Network Learning Algorithm with Approximate Singular Value Decomposition"],"prefix":"10.61822","volume":"29","author":[{"given":"Norbert","family":"Jankowski","sequence":"first","affiliation":[{"name":"Department of Informatics, Faculty of Physics, Astronomy and Informatics , Nicolaus Copernicus University , ul. Grudzi\u0105dzka 5, 87-100 Toru\u0144 , Poland"}]},{"given":"Rafa\u0142","family":"Linowiecki","sequence":"additional","affiliation":[{"name":"Department of Informatics, Faculty of Physics, Astronomy and Informatics , Nicolaus Copernicus University , ul. Grudzi\u0105dzka 5, 87-100 Toru\u0144 , Poland"}]}],"member":"37438","published-online":{"date-parts":[[2019,9,28]]},"reference":[{"key":"2023050302355277878_j_amcs-2019-0043_ref_001_w2aab3b7c12b1b6b1ab1ab1Aa","doi-asserted-by":"crossref","unstructured":"Bishop, C.M. (1991). Training with noise is equivalent to Tikhonov regularization, Neural Computation7(1): 108\u2013116.10.1162\/neco.1995.7.1.108","DOI":"10.1162\/neco.1995.7.1.108"},{"key":"2023050302355277878_j_amcs-2019-0043_ref_002_w2aab3b7c12b1b6b1ab1ab2Aa","doi-asserted-by":"crossref","unstructured":"Boser, B.E., Guyon, I.M. and Vapnik, V. (1992). A training algorithm for optimal margin classifiers, in D. Haussler (Ed.), Proceedings of the 5th Annual ACM Workshop on Computational Learning Theory, Pittsburgh, PA, USA, pp. 144\u2013152.10.1145\/130385.130401","DOI":"10.1145\/130385.130401"},{"key":"2023050302355277878_j_amcs-2019-0043_ref_003_w2aab3b7c12b1b6b1ab1ab3Aa","unstructured":"Broomhead, D.S. and Lowe, D. (1988). Multivariable functional interpolation and adaptive networks, Complex Systems2(3): 321\u2013355."},{"key":"2023050302355277878_j_amcs-2019-0043_ref_004_w2aab3b7c12b1b6b1ab1ab4Aa","doi-asserted-by":"crossref","unstructured":"Dumais, S.T. (2005). Latent semantic analysis, Annual Review of Information Science and Technology38(1): 188\u2013230.10.1002\/aris.1440380105","DOI":"10.1002\/aris.1440380105"},{"key":"2023050302355277878_j_amcs-2019-0043_ref_005_w2aab3b7c12b1b6b1ab1ab5Aa","doi-asserted-by":"crossref","unstructured":"Eirola, E., Lendasse, A., Vandewalle, V. and Biernacki, C. (2014). Mixture of Gaussians for distance estimation with missing data, Neurocomputing131: 32\u201342.10.1016\/j.neucom.2013.07.050","DOI":"10.1016\/j.neucom.2013.07.050"},{"key":"2023050302355277878_j_amcs-2019-0043_ref_006_w2aab3b7c12b1b6b1ab1ab6Aa","unstructured":"Goodfellow, I., Bengio, Y. and Courville, A. (2016). Deep Learning, MIT Press, Cambridge, MA, http:\/\/www.deeplearningbook.org."},{"key":"2023050302355277878_j_amcs-2019-0043_ref_007_w2aab3b7c12b1b6b1ab1ab7Aa","doi-asserted-by":"crossref","unstructured":"G\u00f3recki, T. and \u0141uczak, M. (2013). Linear discriminant analysis with a generalization of the Moore\u2013Penrose pseudoinverse, International Journal of Applied Mathematics and Computer Science23(2): 463\u2013471, DOI: 10.2478\/amcs-2013-0035.10.2478\/amcs-2013-0035","DOI":"10.2478\/amcs-2013-0035"},{"key":"2023050302355277878_j_amcs-2019-0043_ref_008_w2aab3b7c12b1b6b1ab1ab8Aa","doi-asserted-by":"crossref","unstructured":"Halko, N., Martinsson, P.G. and Tropp, J.A. (2011). Finding structure with randomness: Probabilistic algorithms for constructing approximate matrix decompositions, SIAM Review53(2): 217\u2013288.10.1137\/090771806","DOI":"10.1137\/090771806"},{"key":"2023050302355277878_j_amcs-2019-0043_ref_009_w2aab3b7c12b1b6b1ab1ab9Aa","unstructured":"Heseltine, T., Pears, N., Austin, J. and Chen, Z. (2003). Face recognition: A comparison of appearance-based approaches, 7th International Conference on Digital Image Computing: Techniques and Applications, Sydney, Australia, Vol. 1, pp. 59\u201368."},{"key":"2023050302355277878_j_amcs-2019-0043_ref_010_w2aab3b7c12b1b6b1ab1ac10Aa","doi-asserted-by":"crossref","unstructured":"Huang, G.-B., Bai, Z., Kasun, L.L.C. and Vong, C.M. (2015). Local receptive fields based extreme learning machine, IEEE Computational Intelligence Magazine10(2): 18\u201329.10.1109\/MCI.2015.2405316","DOI":"10.1109\/MCI.2015.2405316"},{"key":"2023050302355277878_j_amcs-2019-0043_ref_011_w2aab3b7c12b1b6b1ab1ac11Aa","unstructured":"Huang, G.-B., Zhu, Q.-Y. and Siew, C.-K. (2004). Extreme learning machine: A new learning scheme of feedforward neural networks, International Joint Conference on Neural Networks, Budapest, Hungary, pp. 985\u2013990."},{"key":"2023050302355277878_j_amcs-2019-0043_ref_012_w2aab3b7c12b1b6b1ab1ac12Aa","doi-asserted-by":"crossref","unstructured":"Huang, G.-B., Zhu, Q.-Y. and Siew, C.-K. (2006). Extreme learning machine: Theory and applications, Neurocomputing70(1\u20133): 489\u2013501.10.1016\/j.neucom.2005.12.126","DOI":"10.1016\/j.neucom.2005.12.126"},{"key":"2023050302355277878_j_amcs-2019-0043_ref_013_w2aab3b7c12b1b6b1ab1ac13Aa","unstructured":"Jankowski, N. (2013). Meta-learning and new ways in model construction for classification problems, Journal of Network & Information Security4(4): 275\u2013284."},{"key":"2023050302355277878_j_amcs-2019-0043_ref_014_w2aab3b7c12b1b6b1ab1ac14Aa","doi-asserted-by":"crossref","unstructured":"Jankowski, N. (2018). Comparison of prototype selection algorithms used in construction of neural networks learned by SVD, International Journal of Applied Mathematics and Computer Science28(4): 719\u2013733, DOI: 10.2478\/amcs-2018-0055.10.2478\/amcs-2018-0055","DOI":"10.2478\/amcs-2018-0055"},{"key":"2023050302355277878_j_amcs-2019-0043_ref_015_w2aab3b7c12b1b6b1ab1ac15Aa","unstructured":"Merz, C.J. and Murphy, P.M. (1998). UCI Repository of Machine Learning Databases, https:\/\/archive.ics.uci.edu\/ml\/index.php."},{"key":"2023050302355277878_j_amcs-2019-0043_ref_016_w2aab3b7c12b1b6b1ab1ac16Aa","unstructured":"Mitchell, T. (1997). Machine Learning, McGraw Hill, New York, NY."},{"key":"2023050302355277878_j_amcs-2019-0043_ref_017_w2aab3b7c12b1b6b1ab1ac17Aa","unstructured":"Rumelhart, D.E., Hinton, G.E. and Williams, R.J. (1986). Learning internal representations by error propagation, in J.L.M.D.E. Rumelhart (Ed.), Parallel Distributed Processing: Explorations in Microstructure of Congnition, Vol. 1: Foundations, MIT Press, Cambridge, MA, pp. 318\u2013362."},{"key":"2023050302355277878_j_amcs-2019-0043_ref_018_w2aab3b7c12b1b6b1ab1ac18Aa","doi-asserted-by":"crossref","unstructured":"Sovilj, D., Eirola, E., Miche, Y., Bjork, K.-M., Nian, R., Akusok, A. and Lendasse, A. (2016). Extreme learning machine for missing data using multiple imputations, Neurocomputing174(PA): 220\u2013231.10.1016\/j.neucom.2015.03.108","DOI":"10.1016\/j.neucom.2015.03.108"},{"key":"2023050302355277878_j_amcs-2019-0043_ref_019_w2aab3b7c12b1b6b1ab1ac19Aa","doi-asserted-by":"crossref","unstructured":"Tang, J., Deng, C., Member, S. and Huang, G.-B. (2016). Extreme learning machine for multilayer perceptron, IEEE Transactions on Neural Networks and Learning Systems27(4): 809\u2013821.10.1109\/TNNLS.2015.242499525966483","DOI":"10.1109\/TNNLS.2015.2424995"},{"key":"2023050302355277878_j_amcs-2019-0043_ref_020_w2aab3b7c12b1b6b1ab1ac20Aa","unstructured":"Tikhonov, A.N. and Arsenin, V.Y. (1977). Solutions of Ill-posed Problems, W.H. Winston, Washington, DC."},{"key":"2023050302355277878_j_amcs-2019-0043_ref_021_w2aab3b7c12b1b6b1ab1ac21Aa","doi-asserted-by":"crossref","unstructured":"Vapnik, V. (1995). The Nature of Statistical Learning Theory, Springer-Verlag, New York, NY.10.1007\/978-1-4757-2440-0","DOI":"10.1007\/978-1-4757-2440-0"}],"container-title":["International Journal of Applied Mathematics and Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/content.sciendo.com\/view\/journals\/amcs\/29\/3\/article-p581.xml","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.sciendo.com\/pdf\/10.2478\/amcs-2019-0043","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,29]],"date-time":"2024-02-29T10:29:15Z","timestamp":1709202555000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.sciendo.com\/article\/10.2478\/amcs-2019-0043"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,9,1]]},"references-count":21,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2019,9,28]]},"published-print":{"date-parts":[[2019,9,1]]}},"alternative-id":["10.2478\/amcs-2019-0043"],"URL":"https:\/\/doi.org\/10.2478\/amcs-2019-0043","relation":{},"ISSN":["2083-8492"],"issn-type":[{"value":"2083-8492","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,9,1]]}}}