{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T15:28:37Z","timestamp":1777994917369,"version":"3.51.4"},"reference-count":59,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2019,7,4]],"date-time":"2019-07-04T00:00:00Z","timestamp":1562198400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,7,4]],"date-time":"2019-07-04T00:00:00Z","timestamp":1562198400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"name":"Russian Foundation for Basic Research","award":["18-47-732006"],"award-info":[{"award-number":["18-47-732006"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Process Lett"],"published-print":{"date-parts":[[2020,2]]},"DOI":"10.1007\/s11063-019-10074-0","type":"journal-article","created":{"date-parts":[[2019,7,4]],"date-time":"2019-07-04T14:42:00Z","timestamp":1562251320000},"page":"1-22","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Non-iterative Knowledge Fusion in Deep Convolutional Neural Networks"],"prefix":"10.1007","volume":"51","author":[{"given":"Mikhail Iu.","family":"Leontev","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Viktoriia","family":"Islenteva","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8966-6030","authenticated-orcid":false,"given":"Sergey V.","family":"Sukhov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,7,4]]},"reference":[{"key":"10074_CR1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2908982","author":"J Yu","year":"2019","unstructured":"Yu J, Zhu C, Zhang J et al (2019) Spatial pyramid-enhanced NetVLAD with weighted triplet loss for place recognition. IEEE Trans Neural Netw Learn Syst. \nhttps:\/\/doi.org\/10.1109\/TNNLS.2019.2908982","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"10074_CR2","doi-asserted-by":"crossref","first-page":"4014","DOI":"10.1109\/TCYB.2016.2591583","volume":"47","author":"J Yu","year":"2016","unstructured":"Yu J, Yang X, Gao F, Tao D (2016) Deep multimodal distance metric learning using click constraints for image ranking. IEEE Trans Cybern 47:4014\u20134024","journal-title":"IEEE Trans Cybern"},{"key":"10074_CR3","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1016\/S0079-7421(08)60536-8","volume":"24","author":"M McCloskey","year":"1989","unstructured":"McCloskey M, Cohen NJ (1989) Catastrophic interference in connectionist networks: the sequential learning problem. Psychol Learn Motiv Adv Res Theory 24:109\u2013165. \nhttps:\/\/doi.org\/10.1016\/S0079-7421(08)60536-8","journal-title":"Psychol Learn Motiv Adv Res Theory"},{"key":"10074_CR4","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1037\/0033-295X.97.2.285","volume":"97","author":"R Ratcliff","year":"1990","unstructured":"Ratcliff R (1990) Connectionist models of recognition memory: constraints imposed by learning and forgetting functions. Psychol Rev 97:285\u2013308. \nhttps:\/\/doi.org\/10.1037\/0033-295X.97.2.285","journal-title":"Psychol Rev"},{"key":"10074_CR5","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1023\/A:1007379606734","volume":"28","author":"R Caruana","year":"1997","unstructured":"Caruana R (1997) Multitask learning. Mach Learn 28:41\u201375. \nhttps:\/\/doi.org\/10.1023\/A:1007379606734","journal-title":"Mach Learn"},{"key":"10074_CR6","doi-asserted-by":"crossref","unstructured":"Li Z, Hoiem D (2016) Learning without forgetting. In: Proceedings of the European conference on computer vision (ECCV), pp 614\u2013629","DOI":"10.1007\/978-3-319-46493-0_37"},{"key":"10074_CR7","unstructured":"Donahue J, Jia Y, Vinyals O, et al (2014) DeCAF: a deep convolutional activation feature for generic visual recognition. In: Xing EP, Jebara T (eds) Proceedings of the 31st international conference on machine learning, PMLR, Bejing, China, pp 647\u2013655"},{"key":"10074_CR8","doi-asserted-by":"crossref","unstructured":"Girshick R, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE computer society conference on computer vision and pattern recognition, pp 580\u2013587","DOI":"10.1109\/CVPR.2014.81"},{"key":"10074_CR9","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1007\/978-1-4471-0281-6_2","volume-title":"Connectionist models of learning, development and evolution","author":"RM French","year":"2001","unstructured":"French RM, Ans B, Rousset S (2001) Pseudopatterns and dual\u2010network memory models: advantages and shortcomings. In: French R, Sougn\u00e9 J (eds) Connectionist models of learning, development and evolution. Springer, London, pp 13\u201322"},{"key":"10074_CR10","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-016-9535-1","author":"H Li","year":"2017","unstructured":"Li H, Wang X, Ding S (2017) Research and development of neural network ensembles: a survey. Artif Intell Rev. \nhttps:\/\/doi.org\/10.1007\/s10462-016-9535-1","journal-title":"Artif Intell Rev"},{"key":"10074_CR11","doi-asserted-by":"crossref","unstructured":"Dietterich TG (2000) Ensemble methods in machine learning. In: Multiple classifier systems, pp 1\u201315","DOI":"10.1007\/3-540-45014-9_1"},{"key":"10074_CR12","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman L (2001) Random forests. Mach Learn 45:5\u201332. \nhttps:\/\/doi.org\/10.1023\/A:1010933404324","journal-title":"Mach Learn"},{"key":"10074_CR13","unstructured":"Domingos P (2000) Bayesian averaging of classifiers and the overfitting problem. In: 17th International conference on machine learning, San Francisco, pp 223\u2013230"},{"key":"10074_CR14","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1016\/S0893-6080(05)80023-1","volume":"5","author":"DH Wolpert","year":"1992","unstructured":"Wolpert DH (1992) Stacked generalization. Neural Netw 5:241\u2013259. \nhttps:\/\/doi.org\/10.1016\/S0893-6080(05)80023-1","journal-title":"Neural Netw"},{"key":"10074_CR15","doi-asserted-by":"publisher","first-page":"699","DOI":"10.1007\/s13042-014-0303-8","volume":"6","author":"M Bhardwaj","year":"2015","unstructured":"Bhardwaj M, Bhatnagar V (2015) Towards an optimally pruned classifier ensemble. Int J Mach Learn Cybern 6:699\u2013718. \nhttps:\/\/doi.org\/10.1007\/s13042-014-0303-8","journal-title":"Int J Mach Learn Cybern"},{"key":"10074_CR16","doi-asserted-by":"crossref","unstructured":"Fujii T, Asama H, Fujita T, et al (1996) Knowledge sharing among multiple autonomous mobile robots through indirect communication using intelligent data carriers. In: Proceedings of IEEE\/RSJ international conference on intelligent robots and systems, IROS\u201996. IEEE, pp 1466\u20131471","DOI":"10.1109\/IROS.1996.569007"},{"key":"10074_CR17","doi-asserted-by":"crossref","first-page":"1317","DOI":"10.1109\/TIFS.2017.2787986","volume":"13","author":"J Yu","year":"2018","unstructured":"Yu J, Kuang Z, Zhang B et al (2018) Leveraging content sensitiveness and user trustworthiness to recommend fine-grained privacy settings for social image sharing. IEEE Trans Inf Forensics Secur 13:1317\u20131332","journal-title":"IEEE Trans Inf Forensics Secur"},{"key":"10074_CR18","doi-asserted-by":"crossref","first-page":"388","DOI":"10.18383\/j.tom.2016.00211","volume":"2","author":"R Paul","year":"2016","unstructured":"Paul R, Hawkins SH, Balagurunathan Y et al (2016) Deep feature transfer learning in combination with traditional features predicts survival among patients with lung adenocarcinoma. Tomography 2:388","journal-title":"Tomography"},{"key":"10074_CR19","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1023\/A:1026530200837","volume":"12","author":"X Zeng","year":"2000","unstructured":"Zeng X, Martinez TR (2000) Using a neural network to approximate an ensemble of classifiers. Neural Process Lett 12:225\u2013237","journal-title":"Neural Process Lett"},{"key":"10074_CR20","doi-asserted-by":"crossref","unstructured":"Bucilu\u01ce C, Caruana R, Niculescu-Mizil A (2006) Model compression. In: Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining - KDD\u201906. ACM Press, New York, New York, USA, p 535","DOI":"10.1145\/1150402.1150464"},{"key":"10074_CR21","unstructured":"Hinton G, Vinyals O, Dean J (2015) Distilling the knowledge in a neural network. arXiv Preprint \narXiv:1503.02531"},{"key":"10074_CR22","unstructured":"Papamakarios G (2015) Distilling model knowledge. arXiv Preprint \narXiv:1510.02437"},{"key":"10074_CR23","first-page":"477","volume":"42","author":"C Alexandra","year":"1997","unstructured":"Alexandra C, Cristea P, Okamoto T (1997) Neural network knowledge extraction. Rev Roum des Sci Tech Ser EE (Electrotechn Energ) 42:477\u2013491","journal-title":"Rev Roum des Sci Tech Ser EE (Electrotechn Energ)"},{"key":"10074_CR24","first-page":"71","volume":"13","author":"GG Towell","year":"1993","unstructured":"Towell GG, Shavlik JW (1993) Extracting refined rules from knowledge-based neural networks. Mach Learn 13:71\u2013101","journal-title":"Mach Learn"},{"key":"10074_CR25","doi-asserted-by":"crossref","first-page":"844","DOI":"10.1109\/TNN.2005.849843","volume":"16","author":"E Kolman","year":"2005","unstructured":"Kolman E, Margaliot M (2005) Are artificial neural networks white boxes? IEEE Trans Neural Netw 16:844\u2013852","journal-title":"IEEE Trans Neural Netw"},{"key":"10074_CR26","doi-asserted-by":"crossref","first-page":"493","DOI":"10.1007\/s00500-007-0221-8","volume":"12","author":"CJ Mantas","year":"2008","unstructured":"Mantas CJ (2008) A generic fuzzy aggregation operator: rules extraction from and insertion into artificial neural networks. Soft Comput 12:493\u2013514","journal-title":"Soft Comput"},{"key":"10074_CR27","doi-asserted-by":"crossref","first-page":"384","DOI":"10.1016\/j.neucom.2005.12.127","volume":"70","author":"ER Hruschka","year":"2006","unstructured":"Hruschka ER, Ebecken NFF (2006) Extracting rules from multilayer perceptrons in classification problems: a clustering-based approach. Neurocomputing 70:384\u2013397","journal-title":"Neurocomputing"},{"key":"10074_CR28","doi-asserted-by":"crossref","unstructured":"McGarry KJ, MacIntyre J (1999) Knowledge extraction and insertion from radial basis function networks. In: IEE Colloquium on Applied Statistical Pattern Recognition (Ref. No. 1999\/063), pp 15\/1\u201315\/6","DOI":"10.1049\/ic:19990372"},{"key":"10074_CR29","doi-asserted-by":"crossref","unstructured":"Kasabov N, Woodford B (1999) Rule insertion and rule extraction from evolving fuzzy neural networks: algorithms and applications for building adaptive, intelligent expert systems. In: Proceedings of the FUZZ-IEEE, pp 1406\u20131411","DOI":"10.1109\/FUZZY.1999.790109"},{"key":"10074_CR30","unstructured":"Tran SN, Garcez ADA (2013) Knowledge extraction from deep belief networks for images. In: IJCAI-2013 workshop on neural-symbolic learning and reasoning"},{"key":"10074_CR31","doi-asserted-by":"crossref","first-page":"246","DOI":"10.1109\/TNNLS.2016.2603784","volume":"29","author":"SN Tran","year":"2018","unstructured":"Tran SN, Garcez ADA (2018) Deep logic networks: inserting and extracting knowledge from deep belief networks. IEEE Trans Neural Netw Learn Syst 29:246\u2013258","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"10074_CR32","unstructured":"Utans J (1996) Weight averaging for neural networks and local resampling schemes. In: AAAI-96 Workshop on integrating multiple learned models, pp 133\u2013138"},{"key":"10074_CR33","doi-asserted-by":"crossref","unstructured":"Smith J, Gashler M (2017) An investigation of how neural networks learn from the experiences of peers through periodic weight averaging. In: 2017 16th IEEE international conference on machine learning and applications (ICMLA). IEEE, pp 731\u2013736","DOI":"10.1109\/ICMLA.2017.00-72"},{"key":"10074_CR34","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1007\/s11063-017-9712-5","volume":"48","author":"MI Akhlaghi","year":"2018","unstructured":"Akhlaghi MI, Sukhov SV (2018) Knowledge fusion in feedforward artificial neural networks. Neural Process Lett 48:257\u2013272. \nhttps:\/\/doi.org\/10.1007\/s11063-017-9712-5","journal-title":"Neural Process Lett"},{"key":"10074_CR35","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","volume":"22","author":"SJ Pan","year":"2010","unstructured":"Pan SJ, Yang Q (2010) A survey on transfer learning. IEEE Trans Knowl Data Eng 22:1345\u20131359. \nhttps:\/\/doi.org\/10.1109\/TKDE.2009.191","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"10074_CR36","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4615-5529-2","volume-title":"Learning to learn","author":"S Thrun","year":"1998","unstructured":"Thrun S, Pratt L (1998) Learning to learn. Springer, Berlin"},{"key":"10074_CR37","doi-asserted-by":"crossref","unstructured":"Hu J, Lu J, Tan Y-P (2015) Deep transfer metric learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 325\u2013333","DOI":"10.1109\/CVPR.2015.7298629"},{"key":"10074_CR38","doi-asserted-by":"crossref","unstructured":"Wu Y, Ji Q (2016) Constrained deep transfer feature learning and its applications. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5101\u20135109","DOI":"10.1109\/CVPR.2016.551"},{"key":"10074_CR39","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1007\/s13042-011-0019-y","volume":"2","author":"G-B Huang","year":"2011","unstructured":"Huang G-B, Wang DH, Lan Y (2011) Extreme learning machines: a survey. Int J Mach Learn Cybern 2:107\u2013122","journal-title":"Int J Mach Learn Cybern"},{"key":"10074_CR40","first-page":"1097","volume":"25","author":"A Krizhevsky","year":"2012","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) ImageNet classification with deep convolutional neural networks. Adv Neural Inf Process Syst 25:1097\u20131105","journal-title":"Adv Neural Inf Process Syst"},{"key":"10074_CR41","unstructured":"Blundell C, Cornebise J, Kavukcuoglu K, Wierstra D (2015) Weight uncertainty in neural networks. In: Proceedings of the 32nd international conference on international conference on machine learning-volume 37, JMLR.org, pp 1613\u20131622"},{"key":"10074_CR42","doi-asserted-by":"crossref","unstructured":"Schmidt WF, Kraaijveld MA, Duin RPW (1992) Feedforward neural networks with random weights. In: Proceedings 11th IAPR international conference on pattern recognition, Vol. II. Conference B: pattern recognition methodology and systems. IEEE Computer Society Press, pp 1\u20134","DOI":"10.1109\/ICPR.1992.201708"},{"key":"10074_CR43","doi-asserted-by":"crossref","unstructured":"Bellido I, Fiesler E (1993) Do backpropagation trained neural networks have normal weight distributions? In: ICANN\u201993. Springer, London, pp 772\u2013775","DOI":"10.1007\/978-1-4471-2063-6_214"},{"key":"10074_CR44","doi-asserted-by":"crossref","first-page":"1755","DOI":"10.1162\/08997660260028700","volume":"14","author":"RM French","year":"2002","unstructured":"French RM, Chater N (2002) Using noise to compute error surfaces in connectionist networks: a novel means of reducing catastrophic forgetting. Neural Comput 14:1755\u20131769","journal-title":"Neural Comput"},{"key":"10074_CR45","doi-asserted-by":"crossref","first-page":"3521","DOI":"10.1073\/pnas.1611835114","volume":"114","author":"J Kirkpatrick","year":"2017","unstructured":"Kirkpatrick J, Pascanu R, Rabinowitz N et al (2017) Overcoming catastrophic forgetting in neural networks. Proc Natl Acad Sci 114:3521\u20133526","journal-title":"Proc Natl Acad Sci"},{"key":"10074_CR46","unstructured":"Pascanu R, Bengio Y (2013) Revisiting Natural Gradient for Deep Networks. arXiv Preprint \narXiv:1301.3584"},{"key":"10074_CR47","doi-asserted-by":"publisher","first-page":"480","DOI":"10.1109\/72.286919","volume":"5","author":"WL Buntine","year":"1994","unstructured":"Buntine WL, Weigend AS (1994) Computing second derivatives in feed-forward networks: a review. IEEE Trans Neural Netw 5:480\u2013488. \nhttps:\/\/doi.org\/10.1109\/72.286919","journal-title":"IEEE Trans Neural Netw"},{"key":"10074_CR48","doi-asserted-by":"crossref","unstructured":"Ashmore S, Gashler M (2015) A method for finding similarity between multi-layer perceptrons by Forward Bipartite Alignment. In: 2015 International joint conference on neural networks (IJCNN), IEEE, pp 1\u20137","DOI":"10.1109\/IJCNN.2015.7280769"},{"key":"10074_CR49","doi-asserted-by":"crossref","first-page":"2420","DOI":"10.1109\/TIP.2018.2804218","volume":"27","author":"J Zhang","year":"2018","unstructured":"Zhang J, Yu J, Tao D (2018) Local deep-feature alignment for unsupervised dimension reduction. IEEE Trans Image Process 27:2420\u20132432","journal-title":"IEEE Trans Image Process"},{"key":"10074_CR50","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1002\/nav.3800020109","volume":"2","author":"HW Kuhn","year":"1955","unstructured":"Kuhn HW (1955) The Hungarian algorithm for the assignment problem. Nav Res Logist Q 2:83\u201397","journal-title":"Nav Res Logist Q"},{"key":"10074_CR51","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86:2278\u20132323. \nhttps:\/\/doi.org\/10.1109\/5.726791","journal-title":"Proc IEEE"},{"key":"10074_CR52","unstructured":"Chollet F (2016) Keras: deep learning library for theano and tensorflow. \nhttps:\/\/keras.io\n\n. Accessed 02 July 2019"},{"key":"10074_CR53","unstructured":"Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv Preprint \narXiv:1412.6980"},{"key":"10074_CR54","first-page":"123","volume":"24","author":"L Breiman","year":"1996","unstructured":"Breiman L (1996) Bagging predictors. Mach Learn 24:123\u2013140","journal-title":"Mach Learn"},{"key":"10074_CR55","doi-asserted-by":"crossref","first-page":"256","DOI":"10.1006\/inco.1995.1136","volume":"121","author":"Y Freund","year":"1995","unstructured":"Freund Y (1995) Boosting a weak learning algorithm by majority. Inf Comput 121:256\u2013285","journal-title":"Inf Comput"},{"key":"10074_CR56","unstructured":"Krizhevsky A, Hinton G (2009) Learning multiple layers of features from tiny images. Technical Report, University of Toronto 1:7"},{"key":"10074_CR57","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky O, Deng J, Su H et al (2015) ImageNet large scale visual recognition challenge. Int J Comput Vis 115:211\u2013252. \nhttps:\/\/doi.org\/10.1007\/s11263-015-0816-y","journal-title":"Int J Comput Vis"},{"key":"10074_CR58","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv Preprint \narXiv:1409.1556"},{"key":"10074_CR59","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1016\/j.neunet.2018.01.001","volume":"100","author":"L Zhu","year":"2018","unstructured":"Zhu L, Ikeda K, Pang S et al (2018) Merging weighted SVMs for parallel incremental learning. Neural Netw 100:25\u201338. \nhttps:\/\/doi.org\/10.1016\/j.neunet.2018.01.001","journal-title":"Neural Netw"}],"container-title":["Neural Processing Letters"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-019-10074-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11063-019-10074-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-019-10074-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,7,2]],"date-time":"2020-07-02T23:37:33Z","timestamp":1593733053000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11063-019-10074-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7,4]]},"references-count":59,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2020,2]]}},"alternative-id":["10074"],"URL":"https:\/\/doi.org\/10.1007\/s11063-019-10074-0","relation":{},"ISSN":["1370-4621","1573-773X"],"issn-type":[{"value":"1370-4621","type":"print"},{"value":"1573-773X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,7,4]]},"assertion":[{"value":"4 July 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}