{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T23:20:49Z","timestamp":1781047249082,"version":"3.54.1"},"reference-count":21,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2022,2,8]],"date-time":"2022-02-08T00:00:00Z","timestamp":1644278400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,2,8]],"date-time":"2022-02-08T00:00:00Z","timestamp":1644278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Image Video Proc."],"published-print":{"date-parts":[[2022,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>The paper presents a novel approach for designing the CNN structure of improved generalization capability in the presence of a small population of learning data. Unlike the classical methods for building CNN, we propose to introduce some randomness in the choice of layers with a different type of nonlinear activation function. The image processing in these layers is performed using either the ReLU or the softplus function. This choice is random. The randomness introduced in the network structure can be interpreted as a special form of regularization. Experiments performed on the detection of images belonging to either melanoma or non-melanoma cases have shown a significant improvement in average quality measures such as accuracy, sensitivity, precision, and area under the ROC curve.<\/jats:p>","DOI":"10.1186\/s13640-022-00580-y","type":"journal-article","created":{"date-parts":[[2022,2,7]],"date-time":"2022-02-07T23:46:07Z","timestamp":1644277567000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["Random CNN structure: tool to increase generalization ability in deep learning"],"prefix":"10.1186","volume":"2022","author":[{"given":"Bartosz","family":"Swiderski","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3194-4656","authenticated-orcid":false,"given":"Stanislaw","family":"Osowski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Grzegorz","family":"Gwardys","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jaroslaw","family":"Kurek","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Monika","family":"Slowinska","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Iwona","family":"Lugowska","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,2,8]]},"reference":[{"issue":"6","key":"580_CR1","first-page":"761","volume":"66","author":"T Poggio","year":"2018","unstructured":"T. Poggio, Q. Liao, Theory I: deep networks, the curse of dimensionality, bulletin of the polish academy of sciences. Tech Sci 66(6), 761\u2013773 (2018)","journal-title":"Tech Sci"},{"key":"580_CR2","doi-asserted-by":"publisher","first-page":"15844","DOI":"10.1109\/ACCESS.2018.2810849","volume":"6","author":"Q Zheng","year":"2018","unstructured":"Q. Zheng, M. Yang, J. Yang, Q. Zhang, X. Zhang, Improvement of generalization ability of deep CNN via implicit regularization in two-stage training process. IEEE Access 6, 15844\u201315869 (2018)","journal-title":"IEEE Access"},{"key":"580_CR3","unstructured":"P. Zhou, J. Feng, Understanding generalization, optimization performance of deep CNNs, in Proceedings of the 35th International Conference on Machine Learning, Stockholm, Sweden, PMLR 80 1\u201319 (2018)"},{"issue":"4","key":"580_CR4","doi-asserted-by":"publisher","first-page":"1445","DOI":"10.1109\/TPAMI.2020.2975798","volume":"43","author":"C Yan","year":"2020","unstructured":"C. Yan, B. Gong, Y. Wei, Y. Gao, Deep multi-view enhancement hashing for image retrieval. IEEE Trans Pattern Anal Mach Intell 43(4), 1445\u20131451 (2020). https:\/\/doi.org\/10.1109\/TPAMI.2020.2975798","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"580_CR5","doi-asserted-by":"publisher","DOI":"10.1145\/3404374","author":"C Yan","year":"2020","unstructured":"C. Yan, Z. Li, Y. Zhang, Y. Liu, X. Ji, Y. Zhang, Depth image denoising using nuclear norm and learning graph model. ACM Trans Multimedia Comput Commun Appl (2020). https:\/\/doi.org\/10.1145\/3404374","journal-title":"ACM Trans Multimedia Comput Commun Appl"},{"key":"580_CR6","volume-title":"Statistical learning theory","author":"V Vapnik","year":"1998","unstructured":"V. Vapnik, Statistical learning theory (Wiley, New York, 1998)"},{"key":"580_CR7","volume-title":"Introduction to data mining","author":"PN Tan","year":"2013","unstructured":"P.N. Tan, M. Steinbach, V. Kumar, Introduction to data mining (Pearson Education Inc., Boston, 2013)"},{"key":"580_CR8","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y Bengio","year":"2015","unstructured":"Y. Bengio, Y. LeCun, G. Hinton, Deep learning. Nature 521, 436\u2013444 (2015)","journal-title":"Nature"},{"key":"580_CR9","unstructured":"J. Brownlee, Deep learning for natural language processing. Develop deep learning models for your natural language problems, Ebook, (2018)."},{"key":"580_CR10","volume-title":"Deep learning","author":"I Goodfellow","year":"2016","unstructured":"I. Goodfellow, Y. Bengio, A. Courville, Deep learning (MIT Press, Massachusetts, 2016)"},{"key":"580_CR11","unstructured":"I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, Y. Bengio, Generative adversarial nets. Advances in Neural Information Processing Systems, arXiv: 1406.2661, 1\u20139 (2014)."},{"key":"580_CR12","doi-asserted-by":"publisher","unstructured":"S. Guan, M. Loew, Using generative adversarial networks and transfer learning for breast cancer detection by convolutional neural networks, Proc. SPIE 10954. Medical Imaging 2019: Imaging Informatics for Healthcare, Research, and Applications. (2019). https:\/\/doi.org\/10.1117\/12.2512671","DOI":"10.1117\/12.2512671"},{"key":"580_CR13","unstructured":"H. Ren, J. Su, H. Lu, Evaluating generalization ability of CNN and capsule networks for image classification via top-2 classification, arXiv: 1901.10112v2 [cs.CV], 1\u201318 (2019)"},{"issue":"6","key":"580_CR14","first-page":"831","volume":"66","author":"J Kurek","year":"2018","unstructured":"J. Kurek, B. Swiderski, S. Osowski, M. Kruk, W. Barhoumi, Deep learning versus classical neural approach to mammogram recognition. Bull Polish Acad Sci Tech Sci 66(6), 831\u2013840 (2018)","journal-title":"Bull Polish Acad Sci Tech Sci"},{"key":"580_CR15","doi-asserted-by":"publisher","DOI":"10.1002\/0471660264","volume-title":"Combining pattern classifiers: methods and algorithms","author":"L Kuncheva","year":"2004","unstructured":"L. Kuncheva, Combining pattern classifiers: methods and algorithms (Wiley, New York, 2004)"},{"key":"580_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13640-015-0099-9","volume":"43","author":"M Kruk","year":"2015","unstructured":"M. Kruk, B. \u015awiderski, S. Osowski, J. Kurek, M. S\u0142owi\u0144ska, I. Walecka, Melanoma recognition using extended set of descriptors and classifiers. Eurasip Jo Image Video Proc 43, 1\u201310 (2015). https:\/\/doi.org\/10.1186\/s13640-015-0099-9","journal-title":"Eurasip Jo Image Video Proc"},{"key":"580_CR17","unstructured":"B. Neyshabur, S. Bhojanapalli, D. McAllester, N. Srebro, Exploring generalization in deep learning, NIPS 2017, arXiv: 1706.08947, 1\u201319 (2017)"},{"key":"580_CR18","unstructured":"C. Zhang, S. Bengio, M. Hardt, B. Recht, O. Vinyals, Understanding deep learning requires rethinking generalization, International Conference Learning Representations (ICLR) 2017, arXiv: 1611.03530v2 [cs.LG], 1\u201315 (2017)"},{"key":"580_CR19","unstructured":"Matlab user manual, MathWorks, Inc. Natick, USA, 2017"},{"key":"580_CR20","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1561\/2200000056","volume":"12","author":"P Kingma","year":"2019","unstructured":"P. Kingma, M. Welling, An introduction to variational autoencoders. Found Trends Mach Learn 12, 307\u2013392 (2019)","journal-title":"Found Trends Mach Learn"},{"key":"580_CR21","doi-asserted-by":"publisher","first-page":"3385","DOI":"10.1007\/s00521-020-05182-1","volume":"33","author":"J Kiselak","year":"2021","unstructured":"J. Kiselak, Y. Lu, J. Svihra, P. Szepe, M. Stehlik, SPOCU: scaled polynomial constant unit activation function. Neural Comput. Appl. 33, 3385\u20133401 (2021). https:\/\/doi.org\/10.1007\/s00521-020-05182-1","journal-title":"Neural Comput. Appl."}],"container-title":["EURASIP Journal on Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13640-022-00580-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13640-022-00580-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13640-022-00580-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,2,7]],"date-time":"2022-02-07T23:49:50Z","timestamp":1644277790000},"score":1,"resource":{"primary":{"URL":"https:\/\/jivp-eurasipjournals.springeropen.com\/articles\/10.1186\/s13640-022-00580-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,8]]},"references-count":21,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2022,12]]}},"alternative-id":["580"],"URL":"https:\/\/doi.org\/10.1186\/s13640-022-00580-y","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-277475\/v1","asserted-by":"object"}]},"ISSN":["1687-5281"],"issn-type":[{"value":"1687-5281","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,2,8]]},"assertion":[{"value":"26 February 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 January 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 February 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"There are no financial competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"3"}}