{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T06:49:29Z","timestamp":1778827769445,"version":"3.51.4"},"reference-count":192,"publisher":"Springer Science and Business Media LLC","issue":"16","license":[{"start":{"date-parts":[[2022,5,25]],"date-time":"2022-05-25T00:00:00Z","timestamp":1653436800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,5,25]],"date-time":"2022-05-25T00:00:00Z","timestamp":1653436800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2022,8]]},"DOI":"10.1007\/s00521-022-07366-3","type":"journal-article","created":{"date-parts":[[2022,5,25]],"date-time":"2022-05-25T02:03:24Z","timestamp":1653444204000},"page":"13371-13385","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":349,"title":["Attention mechanism in neural networks: where it comes and where it goes"],"prefix":"10.1007","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3212-6711","authenticated-orcid":false,"given":"Derya","family":"Soydaner","sequence":"first","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,5,25]]},"reference":[{"key":"7366_CR1","volume-title":"Deep learning","author":"I Goodfellow","year":"2016","unstructured":"Goodfellow I, Bengio Y, Courville A (2016) Deep learning. The MIT Press"},{"issue":"6","key":"7366_CR2","first-page":"34","volume":"224","author":"D Noton","year":"1971","unstructured":"Noton D, Stark L (1971) Eye movements and visual perception. Sci Am 224(6):34","journal-title":"Sci Am"},{"key":"7366_CR3","doi-asserted-by":"publisher","first-page":"929","DOI":"10.1016\/0042-6989(71)90213-6","volume":"11","author":"D Noton","year":"1971","unstructured":"Noton D, Stark L (1971) Scanpaths in saccadic eye movements while viewing and recognizing patterns. Vision Res 11:929","journal-title":"Vision Res"},{"key":"7366_CR4","first-page":"771","volume":"8","author":"E Alpayd\u0131n","year":"1995","unstructured":"Alpayd\u0131n E (1995) Selective attention for handwritten digit recognition. Adv Neural Inf Process Syst 8:771\u2013777","journal-title":"Adv Neural Inf Process Syst"},{"key":"7366_CR5","first-page":"420","volume":"4","author":"S Ahmad","year":"1991","unstructured":"Ahmad S (1991) VISIT: a neural model of covert visual attention. Adv Neural Inf Process Syst 4:420\u2013427","journal-title":"Adv Neural Inf Process Syst"},{"issue":"1","key":"7366_CR6","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1146\/annurev.ne.13.030190.000325","volume":"13","author":"M Posner","year":"1990","unstructured":"Posner M, Petersen S (1990) The attention system of the human brain. Annu Rev Neurosci 13(1):25","journal-title":"Annu Rev Neurosci"},{"issue":"4","key":"7366_CR7","doi-asserted-by":"publisher","first-page":"523","DOI":"10.1037\/0033-295X.97.4.523","volume":"97","author":"C Bundesen","year":"1990","unstructured":"Bundesen C (1990) A theory of visual attention. Psychol Rev 97(4):523","journal-title":"Psychol Rev"},{"issue":"1","key":"7366_CR8","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1146\/annurev.ne.18.030195.001205","volume":"18","author":"R Desimone","year":"1995","unstructured":"Desimone R, Duncan J (1995) Neural mechanisms of selective visual attention. Annu Rev Neurosci 18(1):193","journal-title":"Annu Rev Neurosci"},{"issue":"3","key":"7366_CR9","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1038\/nrn755","volume":"3","author":"M Corbetta","year":"2002","unstructured":"Corbetta M, Shulman G (2002) Control of goal-directed and stimulus-driven attention in the brain. Nat Rev Neurosci 3(3):201","journal-title":"Nat Rev Neurosci"},{"key":"7366_CR10","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1146\/annurev-neuro-062111-150525","volume":"35","author":"S Petersen","year":"2012","unstructured":"Petersen S, Posner M (2012) The attention system of the human brain: 20 years after. Annu Rev Neurosci 35:73","journal-title":"Annu Rev Neurosci"},{"key":"7366_CR11","unstructured":"Rimey R, Brown C (1990) Selective attention as sequential behaviour: modeling eye movements with an augmented hidden markov model, Technical Report, University of Rochester"},{"issue":"3","key":"7366_CR12","doi-asserted-by":"publisher","first-page":"507","DOI":"10.1007\/BF00233988","volume":"98","author":"B Sheliga","year":"1994","unstructured":"Sheliga B, Riggio L, Rizzolatti G (1994) Orienting of attention and eye movements. Exp Brain Res 98(3):507","journal-title":"Exp Brain Res"},{"issue":"2","key":"7366_CR13","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1007\/BF00240962","volume":"105","author":"B Sheliga","year":"1995","unstructured":"Sheliga B, Riggio L, Rizzolatti G (1995) Spatial attention and eye movements. Exp Brain Res 105(2):261","journal-title":"Exp Brain Res"},{"issue":"6","key":"7366_CR14","doi-asserted-by":"publisher","first-page":"787","DOI":"10.3758\/BF03206794","volume":"57","author":"J Hoffman","year":"1995","unstructured":"Hoffman J, Subramaniam B (1995) The role of visual attention in saccadic eye movements. Percept Psychophys 57(6):787","journal-title":"Percept Psychophys"},{"key":"7366_CR15","doi-asserted-by":"crossref","unstructured":"Chaudhari S et al (2021) An attentive survey of attention models, ACM Transactions on Intelligent Systems and Technology (TIST) pp 1\u201332","DOI":"10.1145\/3465055"},{"key":"7366_CR16","doi-asserted-by":"publisher","first-page":"4291","DOI":"10.1109\/TNNLS.2020.3019893","volume":"32","author":"A Galassi","year":"2020","unstructured":"Galassi A et al (2020) Attention in natural language processing. IEEE Trans Neural Netw Learn Syst 32:4291\u20134308","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"issue":"6","key":"7366_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3363574","volume":"13","author":"J Lee","year":"2019","unstructured":"Lee J et al (2019) Attention models in graphs: a survey. ACM Trans Knowl Discov Data (TKDD) 13(6):1","journal-title":"ACM Trans Knowl Discov Data (TKDD)"},{"key":"7366_CR18","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown T et al (2020) Language models are few-shot learners. Adv Neural Inf Process Syst 33:1877\u20131901","journal-title":"Adv Neural Inf Process Syst"},{"key":"7366_CR19","first-page":"5998","volume":"30","author":"A Vaswani","year":"2017","unstructured":"Vaswani A et al (2017) Attention is all you need. Adv Neural Inf Process Syst 30:5998\u20136008","journal-title":"Adv Neural Inf Process Syst"},{"key":"7366_CR20","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1007\/BF00344251","volume":"36","author":"K Fukushima","year":"1980","unstructured":"Fukushima K (1980) Neocognitron: a self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biol Cybern 36:193","journal-title":"Biol Cybern"},{"issue":"23","key":"7366_CR21","doi-asserted-by":"publisher","first-page":"4985","DOI":"10.1364\/AO.26.004985","volume":"26","author":"K Fukushima","year":"1987","unstructured":"Fukushima K (1987) Neural network model for selective attention in visual pattern recognition and associative recall. Appl Opt 26(23):4985","journal-title":"Appl Opt"},{"issue":"1","key":"7366_CR22","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1016\/S0893-6080(05)80071-1","volume":"6","author":"K Fukushima","year":"1993","unstructured":"Fukushima K, Imagawa T (1993) Recognition and segmentation of connected characters with selective attention. Neural Netw 6(1):33","journal-title":"Neural Netw"},{"issue":"6","key":"7366_CR23","doi-asserted-by":"publisher","first-page":"993","DOI":"10.1016\/S0893-6080(97)00034-8","volume":"10","author":"E Postma","year":"1997","unstructured":"Postma E, den Herik HV, Hudson P (1997) SCAN: a scalable model of attentional selection. Neural Netw 10(6):993","journal-title":"Neural Netw"},{"key":"7366_CR24","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1142\/S012906579100011X","volume":"2","author":"J Schmidhuber","year":"1991","unstructured":"Schmidhuber J, Huber R (1991) Learning to generate artificial fovea trajectories for target detection. Int J Neural Syst 2:125\u2013134","journal-title":"Int J Neural Syst"},{"key":"7366_CR25","doi-asserted-by":"crossref","unstructured":"Milanese R et al (1994) Integration of bottom-up and top-down cues for visual attention using non-linear relaxation. In: IEEE computer society conference on computer vision and pattern recoginition, Seattle, WA, pp 781\u2013785","DOI":"10.1109\/CVPR.1994.323898"},{"issue":"1\u20132","key":"7366_CR26","doi-asserted-by":"publisher","first-page":"507","DOI":"10.1016\/0004-3702(95)00025-9","volume":"78","author":"J Tsotsos","year":"1995","unstructured":"Tsotsos J et al (1995) Modeling visual attention via selective tuning. Artif Intell 78(1\u20132):507","journal-title":"Artif Intell"},{"key":"7366_CR27","doi-asserted-by":"crossref","unstructured":"Culhane S, Tsotsos J (1992) A prototype for data-driven visual attention. In: Proceedings of the 11th IAPR international conference on pattern recognition, The Hague, pp 36\u201340","DOI":"10.1109\/ICPR.1992.201502"},{"issue":"2","key":"7366_CR28","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1007\/BF01418978","volume":"14","author":"D Reisfeld","year":"1995","unstructured":"Reisfeld D, Wolfson H (1995) Yeshurun Y, Context-free attentional operators: the generalized symmetry transform. Int J Comput Vis 14(2):119","journal-title":"Int J Comput Vis"},{"issue":"15\u201316","key":"7366_CR29","doi-asserted-by":"publisher","first-page":"2387","DOI":"10.1016\/S0042-6989(98)00020-0","volume":"38","author":"I Rybak","year":"1998","unstructured":"Rybak I et al (1998) A model of attention-guided visual perception and recognition. Vis Res 38(15\u201316):2387","journal-title":"Vis Res"},{"issue":"3","key":"7366_CR30","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1007\/s100440050033","volume":"2","author":"J Keller","year":"1999","unstructured":"Keller J et al (1999) Object recognition based on human saccadic behaviour. Pattern Anal Appl 2(3):251\u2013263","journal-title":"Pattern Anal Appl"},{"key":"7366_CR31","doi-asserted-by":"crossref","unstructured":"Miau F, Itti L (2001) A neural model combining attentional orienting to object recognition: preliminary explorations on the interplay between where and what. In: Proceedings of the 23rd annual international conference of the IEEE engineering in medicine and biology society, Istanbul, pp 789\u2013792","DOI":"10.1109\/IEMBS.2001.1019059"},{"key":"7366_CR32","first-page":"1609","volume":"19","author":"W Zhang","year":"2006","unstructured":"Zhang W et al (2006) A computational model of eye movements during object class detection. Adv Neural Inf Process Syst 19:1609\u20131616","journal-title":"Adv Neural Inf Process Syst"},{"issue":"3","key":"7366_CR33","doi-asserted-by":"publisher","first-page":"420","DOI":"10.1109\/34.990146","volume":"24","author":"A Salah","year":"2002","unstructured":"Salah A, Alpayd\u0131n E, Akarun L (2002) A selective attention-based method for visual pattern recognition with application to handwritten digit recognition and face recognition. IEEE Trans Pattern Anal Mach Intell 24(3):420","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"7366_CR34","first-page":"472","volume-title":"Bu\u00a8lthoff HH","author":"D Walther","year":"2002","unstructured":"Walther D et al (2002) Attentional selection for object recognition\u2014A gentle way. In: Bu\u00a8lthoff HH, Wallraven C, Lee SW, Poggio TA (eds) International workshop on biologically motivated computer vision. Springer, Berlin, Heidelberg, pp 472\u2013479"},{"issue":"1","key":"7366_CR35","doi-asserted-by":"publisher","first-page":"152","DOI":"10.1117\/1.1329627","volume":"10","author":"K Schill","year":"2001","unstructured":"Schill K et al (2001) Scene analysis with saccadic eye movements: top-down and bottom-up modeling. J Electron Imaging 10(1):152","journal-title":"J Electron Imaging"},{"key":"7366_CR36","doi-asserted-by":"crossref","unstructured":"Paletta L, Fritz G, Seifert C (2005) Q-learning of sequential attention for visual object recognition from informative local descriptors. In: International conference on machine learning","DOI":"10.1145\/1102351.1102433"},{"issue":"5","key":"7366_CR37","doi-asserted-by":"publisher","first-page":"802","DOI":"10.1109\/TPAMI.2006.86","volume":"28","author":"O.L Meur","year":"2006","unstructured":"Meur O.L (2006) A coherent computational approach to model bottom-up visual attention. IEEE Trans Pattern Anal Mach Intell 28(5):802","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"7366_CR38","unstructured":"Gould S et al (2007) Peripheral-foveal vision for real-time object recognition and tracking in video. In: International joint conference on artificial intelligence (IJCAI) pp 2115\u20132121"},{"key":"7366_CR39","first-page":"1243","volume":"23","author":"H Larochelle","year":"2010","unstructured":"Larochelle H, Hinton G (2010) Learning to combine foveal glimpses with a third-order Boltzmann machine. Adv Neural Inf Process Syst 23:1243\u20131251","journal-title":"Adv Neural Inf Process Syst"},{"key":"7366_CR40","unstructured":"Bazzani L et al (2011) Learning attentional policies for tracking and recognition in video with deep networks"},{"key":"7366_CR41","first-page":"2204","volume":"27","author":"V Mnih","year":"2014","unstructured":"Mnih V et al (2014) Recurrent models of visual attention. Adv Neural Inf Process Syst 27:2204\u20132212","journal-title":"Adv Neural Inf Process Syst"},{"key":"7366_CR42","first-page":"3545","volume":"27","author":"M Stollenga","year":"2014","unstructured":"Stollenga M et al (2014) Deep networks with internal selective attention through feedback connections. Adv Neural Inf Process Syst 27:3545\u20133553","journal-title":"Adv Neural Inf Process Syst"},{"key":"7366_CR43","unstructured":"Tang Y, Srivastava N, Salakhutdinov R (2014) Learning generative models with visual attention. Advances in Neural Information Processing Systems, 27"},{"key":"7366_CR44","unstructured":"Bahdanau D, Cho K, Bengio Y (2015) Neural machine translation by jointly learning to align and translate"},{"key":"7366_CR45","first-page":"3104","volume":"27","author":"I Sutskever","year":"2014","unstructured":"Sutskever I, Vinyals O, Le Q (2014) Sequence to sequence learning with neural networks. Adv Neural Inf Process Syst 27:3104\u20133112","journal-title":"Adv Neural Inf Process Syst"},{"key":"7366_CR46","doi-asserted-by":"crossref","unstructured":"Cho K et al (2014) Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP) pp 1724\u20131734","DOI":"10.3115\/v1\/D14-1179"},{"issue":"11","key":"7366_CR47","doi-asserted-by":"publisher","first-page":"2673","DOI":"10.1109\/78.650093","volume":"45","author":"M Schuster","year":"1997","unstructured":"Schuster M, Paliwal K (1997) Bidirectional recurrent neural networks. IEEE Trans Signal Process 45(11):2673","journal-title":"IEEE Trans Signal Process"},{"key":"7366_CR48","unstructured":"Xu K et al (2015) Show, attend and tell: Neural image caption generation with visual attention. In: International conference on machine learning, pp 2048\u20132057"},{"key":"7366_CR49","doi-asserted-by":"crossref","unstructured":"Vinyals O et al (2015) Show and tell: a neural image caption generator. In: In proceedings of the IEEE conference on computer vision and pattern recognition, pp 3156\u20133164","DOI":"10.1109\/CVPR.2015.7298935"},{"issue":"3\u20134","key":"7366_CR50","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1007\/BF00992696","volume":"8","author":"R Williams","year":"1992","unstructured":"Williams R (1992) Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach Learn 8(3\u20134):229","journal-title":"Mach Learn"},{"key":"7366_CR51","doi-asserted-by":"crossref","unstructured":"Luong MT, Manning HPC (2015) Effective approaches to attention-based neural machine translation. In: Proceedings of the 2015 conference on empirical methods in natural language processing, Lisbon, pp 1412\u20131421","DOI":"10.18653\/v1\/D15-1166"},{"key":"7366_CR52","unstructured":"Lu J et al (2016) Hierarchical question-image co-attention for visual question answering. Advances in Neural Information Processing Systems. 29"},{"key":"7366_CR53","unstructured":"Weston J, Chopra S, Bordes A (2014) Memory networks"},{"key":"7366_CR54","unstructured":"Graves A, Wayne G, Danihelka I.(2014) Neural Turing Machines, arXiv preprint arXiv:1410.5401"},{"key":"7366_CR55","first-page":"2440","volume":"28","author":"S Sukhbaatar","year":"2015","unstructured":"Sukhbaatar S et al (2015) End-to-end memory networks. Adv Neural Inf Process Syst 28:2440\u20132448","journal-title":"Adv Neural Inf Process Syst"},{"key":"7366_CR56","doi-asserted-by":"crossref","unstructured":"Cheng J, Dong L, Lapata M (2016) Long short-term memory-networks for machine reading. In: Proceedings of the 2016 conference on empirical methods in natural language processing, pp 551\u2013561","DOI":"10.18653\/v1\/D16-1053"},{"key":"7366_CR57","doi-asserted-by":"crossref","unstructured":"Parikh A et al (2016) A decomposable attention model for natural language inference. In: Proceedings of the 2016 conference on empirical methods in natural language processing, Austin, Texas, pp 2249\u20132255","DOI":"10.18653\/v1\/D16-1244"},{"key":"7366_CR58","doi-asserted-by":"crossref","unstructured":"You Q et al (2016) Image captioning with semantic attention. In: In proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), Las Vegas, NV, pp 4651\u20134659","DOI":"10.1109\/CVPR.2016.503"},{"key":"7366_CR59","doi-asserted-by":"crossref","unstructured":"Rush A, Chopra S, Weston J (2015) A neural attention model for sentence summarization. In: Proceedings of the 2015 conference on empirical methods in natural language processing, Lisbon, pp 379\u2013389","DOI":"10.18653\/v1\/D15-1044"},{"key":"7366_CR60","doi-asserted-by":"crossref","unstructured":"Yu D et al (2016) Deep convolutional neural networks with layer-wise context expansion and attention, Interspeech pp 17\u201321","DOI":"10.21437\/Interspeech.2016-251"},{"key":"7366_CR61","first-page":"577","volume":"28","author":"J Chorowski","year":"2015","unstructured":"Chorowski J et al (2015) Attention-based models for speech recognition. Adv Neural Inf Process Syst 28:577\u2013585","journal-title":"Adv Neural Inf Process Syst"},{"key":"7366_CR62","doi-asserted-by":"crossref","unstructured":"Zanfir M, Marinoiu E, Sminchisescu C (2016) Spatio-temporal attention models for grounded video captioning. In: Asian conference on computer vision. Springer, Cham, pp 104\u2013119","DOI":"10.1007\/978-3-319-54190-7_7"},{"key":"7366_CR63","unstructured":"Cheng Y et al (2016) Agreement-based joint training for bidirectional attention-based neural machine translation. In: Proceedings of the 25th international joint conference on artificial intelligence"},{"key":"7366_CR64","unstructured":"Rockt T (2016) Reasoning about entailment with neural attention"},{"key":"7366_CR65","doi-asserted-by":"crossref","unstructured":"Y.\u00a0Zhu, et\u00a0al.,(2016) Visual7W:Grounded question answering in images, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition pp. 4995\u20135004","DOI":"10.1109\/CVPR.2016.540"},{"key":"7366_CR66","unstructured":"Chen K et al (2015) ABC-CNN: An attention based convolutional neural network for visual question answering, arXiv preprint arXiv:1511.05960"},{"key":"7366_CR67","doi-asserted-by":"crossref","unstructured":"Xu H, Saenko K (2016) Ask, attend and answer: exploring question-guided spatial attention for visual question answering. In: In European conference on computer vision, pp 451\u2013466","DOI":"10.1007\/978-3-319-46478-7_28"},{"key":"7366_CR68","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1162\/tacl_a_00097","volume":"4","author":"W Yin","year":"2016","unstructured":"Yin W et al (2016) ABCNN: Attention-based convolutional neural network for modeling sentence pairs. Trans Assoc Comput Linguist 4:259","journal-title":"Trans Assoc Comput Linguist"},{"key":"7366_CR69","unstructured":"Sharma S, Kiros R, Salakhutdinov R (2016) Action recognition using visual attention"},{"key":"7366_CR70","doi-asserted-by":"crossref","unstructured":"Yang Z et al (2016) Stacked attention networks for image question answering. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 21\u201329","DOI":"10.1109\/CVPR.2016.10"},{"key":"7366_CR71","unstructured":"Sorokin I et al (2015) Deep attention recurrent Q-network, arXiv preprint arXiv:1512.01693"},{"key":"7366_CR72","first-page":"2593","volume":"28","author":"J Ba","year":"2015","unstructured":"Ba J et al (2015) Learning wake-sleep recurrent attention models. Adv Neural Inf Process Syst 28:2593\u20132601","journal-title":"Adv Neural Inf Process Syst"},{"key":"7366_CR73","unstructured":"Gregor K et al (2015) DRAW: a recurrent neural network for image generation. In: International conference on machine learning, pp 1462\u20131471"},{"key":"7366_CR74","unstructured":"Mansimov E et al (2016) Generating images from captions with attention. In: International conference on learning representations"},{"key":"7366_CR75","first-page":"217","volume":"29","author":"S Reed","year":"2016","unstructured":"Reed S et al (2016) Learning what and where to draw. Adv Neural Inf Process Syst 29:217\u2013225","journal-title":"Adv Neural Inf Process Syst"},{"key":"7366_CR76","doi-asserted-by":"crossref","unstructured":"Voita E et al (2019) Analyzing multi-head self-attention: specialized heads do the heavy lifting, the rest can be pruned. In: In proceedings of the 57th annual meeting of the association for computational linguistics, florence, pp 5797\u20135808","DOI":"10.18653\/v1\/P19-1580"},{"key":"7366_CR77","unstructured":"Kerg G et al (2020) Untangling tradeoffs between recurrence and self-attention in neural networks. Advances in Neural Information Processing Systems, 33"},{"key":"7366_CR78","unstructured":"Cordonnier JB, Loukas A, Jaggi M (2020) On the relationship between self-attention and convolutional layers"},{"key":"7366_CR79","unstructured":"Lin Z et al (2017) A structured self-attentive sentence embedding. In: International conference on learning representations"},{"key":"7366_CR80","unstructured":"Paulus R, Xiong C, Socher R (2018) A deep reinforced model for abstractive summarization. In: International conference on learning representations"},{"key":"7366_CR81","doi-asserted-by":"crossref","unstructured":"Kitaev N, Klein D (2018) Constituency parsing with a self-attentive encoder. In: In proceedings of the 56th annual meeting of the association for computational linguistics (Long papers) pp 2676\u20132686","DOI":"10.18653\/v1\/P18-1249"},{"key":"7366_CR82","doi-asserted-by":"crossref","unstructured":"Povey D et al (2018) A time-restricted self-attention layer for ASR. In: IEEE international conference on acoustics, speech and signal processing (ICASSP), IEEE, pp 5874\u20135878","DOI":"10.1109\/ICASSP.2018.8462497"},{"key":"7366_CR83","unstructured":"Vyas A et al (2020) Fast transformers with clustered attention. Advances in Neural Information Processing Systems, 33"},{"key":"7366_CR84","doi-asserted-by":"crossref","unstructured":"Chan W et al (2016) Listen, attend and spell: a neural network for large vocabulary conversational speech recognition. In: IEEE international conference on acoustics, speech and signal processing (ICASSP), Shanghai, pp 4960\u20134964","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"7366_CR85","doi-asserted-by":"crossref","unstructured":"Sperber M et al (2018) Self-attentional acoustic models. In: In proceedings of annual conference of the international speech communication association (InterSpeech), pp 3723\u20133727","DOI":"10.21437\/Interspeech.2018-1910"},{"key":"7366_CR86","unstructured":"Kaiser L et al (2017) One model to learn them all. arXiv preprint arXiv:1706.05137"},{"key":"7366_CR87","doi-asserted-by":"crossref","unstructured":"Xu C et al (2018) Cross-target stance classification with self-attention networks. In: Proceedings of the 56th annual meeting of the association for computational linguistics (Short papers), Melbourne, pp 778\u2013783","DOI":"10.18653\/v1\/P18-2123"},{"key":"7366_CR88","doi-asserted-by":"crossref","unstructured":"Maruf S, Martins A, Haffari G (2019) Selective attention for context-aware neural machine translation. In: Proceedings of NAACL-HLT, Minneapolis, Minnesota, pp 3092\u20133102","DOI":"10.18653\/v1\/N19-1313"},{"key":"7366_CR89","first-page":"68","volume":"32","author":"P Ramachandran","year":"2019","unstructured":"Ramachandran P et al (2019) Stand-alone self-attention in vision models. Adv Neural Inf Process Syst 32:68\u201380","journal-title":"Adv Neural Inf Process Syst"},{"key":"7366_CR90","unstructured":"Li Y et al (2019) Area attention"},{"key":"7366_CR91","first-page":"2672","volume":"27","author":"I Goodfellow","year":"2014","unstructured":"Goodfellow I et al (2014) Generative adversarial networks. Adv Neural Inf Process Syst 27:2672\u20132680","journal-title":"Adv Neural Inf Process Syst"},{"key":"7366_CR92","unstructured":"Zhang H et al (2019) Self-attention generative adversarial networks. In: International conference on machine learning, pp 7354\u20137363"},{"key":"7366_CR93","doi-asserted-by":"crossref","unstructured":"Xu T et al (2018) Attn GAN: fine-grained text to image generation with attentional generative adversarial networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR) pp 1316\u20131324","DOI":"10.1109\/CVPR.2018.00143"},{"key":"7366_CR94","unstructured":"Yu A et al (2018) QANet: combining local convolution with global self-attention for reading comprehension. In: International conference on learning representations"},{"key":"7366_CR95","unstructured":"Zhang J et al (2018) Ga AN: gated attention networks for learning on large and spatiotemporal graphs. In: Conference on uncertainty in artificial intelligence"},{"key":"7366_CR96","unstructured":"Romero D et al (2020) Attentive group equivariant convolutional networks"},{"key":"7366_CR97","first-page":"3159","volume":"33","author":"R Al-Rfou","year":"2019","unstructured":"Al-Rfou R et al (2019) Character-level language modeling with deeper self-attention. AAAI Conf Artif Intell 33:3159","journal-title":"AAAI Conf Artif Intell"},{"key":"7366_CR98","doi-asserted-by":"crossref","unstructured":"Du J et al (2018) Multi-level structured self-attentions for distantly supervised relation extraction. In: Proceedings of the 2018 conference on empirical methods in natural language processing, pp 2216\u20132225","DOI":"10.18653\/v1\/D18-1245"},{"key":"7366_CR99","unstructured":"Li X et al (2020) SAC: accelerating and structuring self-attention via sparse adaptive connection. Advances in Neural Information Processing Systems, 33"},{"key":"7366_CR100","first-page":"387","volume":"33","author":"B Yang","year":"2019","unstructured":"Yang B et al (2019) Context-aware self-attention networks. AAAI Conf Artif Intell 33:387","journal-title":"AAAI Conf Artif Intell"},{"key":"7366_CR101","doi-asserted-by":"crossref","unstructured":"Yang B et al (2018) Modeling localness for self-attention networks. In: Proceedings of the 2018 conference on empirical methods in natural language processing, Brussels, Belgium, pp 4449\u20134458","DOI":"10.18653\/v1\/D18-1475"},{"key":"7366_CR102","unstructured":"Attention augmented convolutional networks. In: Proceedings of the IEEE international conference on computer vision, pp 3286\u20133295"},{"key":"7366_CR103","doi-asserted-by":"crossref","unstructured":"Shaw P, Uszkoreit J, Vaswani A (2018) Self-attention with relative position representations. In: Proceedings of NAACL-HLT, New Orleans, Louisiana, pp 464\u2013468","DOI":"10.18653\/v1\/N18-2074"},{"key":"7366_CR104","unstructured":"Shen T et al (2018) Di SAN: directional self-attention network for RNN\/CNN-free language understanding. In: AAAI Conference on artificial intelligence, pp 5446\u20135455"},{"key":"7366_CR105","doi-asserted-by":"crossref","unstructured":"Shen T et al (2018) Reinforced self-attention network: a hybrid of hard and soft attention for sequence modeling. In: Proceedings of the 27th international joint conference on artificial intelligence (IJCAI-18), pp 4345\u20134352","DOI":"10.24963\/ijcai.2018\/604"},{"key":"7366_CR106","unstructured":"Le H, Tran T, Venkatesh S (2020) Self-attentive associative memory"},{"key":"7366_CR107","unstructured":"Shen T et al (2018) Bi-directional block self-attention for fast and memory-efficient sequence modeling. In: International conference on learning representations"},{"key":"7366_CR108","unstructured":"Bhojanapalli S et al (2020) Low-rank bottleneck in multi-head attention models"},{"key":"7366_CR109","unstructured":"Tay Y et al (2020) Sparse sinkhorn attention"},{"key":"7366_CR110","doi-asserted-by":"crossref","unstructured":"Sukhbaatar S et al (2019) Adaptive attention span in transformers. In: Proceedings of the 57th annual meeting of the association for computational linguistics, Florence, pp 331\u2013335","DOI":"10.18653\/v1\/P19-1032"},{"key":"7366_CR111","unstructured":"Jernite Y et al (2017) Variable computation in recurrent neural networks. In: International conference on learning representations"},{"key":"7366_CR112","doi-asserted-by":"crossref","unstructured":"Shu R, Nakayama H (2017) An empirical study of adequate vision span for attention-based neural machine translation. In: Proceedings of the first workshop on neural machine translation, Vancouver, pp 1\u201310","DOI":"10.18653\/v1\/W17-3201"},{"key":"7366_CR113","doi-asserted-by":"crossref","unstructured":"Hao J et al (2019) Modeling recurrence for transformer. In: Proceedings of NAACL-HLT, Minneapolis, Minnesota, pp 1198\u20131207","DOI":"10.18653\/v1\/N19-1122"},{"key":"7366_CR114","unstructured":"Huang X et al (2020) Improving transformer optimization through better initialization"},{"key":"7366_CR115","first-page":"12081","volume":"32","author":"V Shiv","year":"2019","unstructured":"Shiv V, Quirk C (2019) Novel positional encodings to enable tree-based transformers. Adv Neural Inf Process Syst 32:12081\u201312091","journal-title":"Adv Neural Inf Process Syst"},{"key":"7366_CR116","unstructured":"Li Z et al (2020) Train large, then compress: rethinking model size for efficient training and inference of transformers"},{"key":"7366_CR117","unstructured":"Hoshen Y (2017) VAIN: Attentional Multi-agent predictive modeling, Advances in Neural Information Processing Systems, 30, Long Beach, CA"},{"key":"7366_CR118","unstructured":"Hu S et al (2021) UPDeT: universal multi-agent reinforcement learning via policy decoupling with transformers. In: International conference on learning representations"},{"key":"7366_CR119","unstructured":"Parisotto E, Salakhutdinov R (2021) Efficient transformers in reinforcement learning using actor-learner distillation"},{"key":"7366_CR120","unstructured":"Wu S et al (2020) Adversarial sparse transformer for time series forecasting. Advances in Neural Information Processing Systems, 33"},{"key":"7366_CR121","doi-asserted-by":"crossref","unstructured":"Bosselut A et al (2019) COMET: commonsense transformers for automatic knowledge graph construction. In: Proceedings of the 57th annual meeting of the association for computational linguistics","DOI":"10.18653\/v1\/P19-1470"},{"key":"7366_CR122","unstructured":"So D, Liang C, Le Q (2019) The evolved transformer"},{"key":"7366_CR123","unstructured":"Choi K et al (2020) Encoding musical style with transformer autoencoders"},{"key":"7366_CR124","first-page":"21981","volume":"33","author":"C Doersch","year":"2020","unstructured":"Doersch C, Gupta A, Zisserman A (2020) Cross Transformers: spatially-aware few-shot transfer. Adv Neural Inf Process Syst 33:21981\u201321993","journal-title":"Adv Neural Inf Process Syst"},{"key":"7366_CR125","doi-asserted-by":"crossref","unstructured":"Carion N et al (2020) End-to-end object detection with transformers. In: European conference on computer vision, pp 213\u2013229","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"7366_CR126","unstructured":"Zhu X et al (2021) Deformable DETR: deformable transformers for end-to-end object detection. In: International conference on learning representations"},{"key":"7366_CR127","unstructured":"Liu X et al (2020) Learning to encode position for transformer with continuous dynamical model. In: International conference on machine learning, pp 6327\u20136335"},{"key":"7366_CR128","unstructured":"Kasai J et al (2020) Non-autoregressive machine translation with disentangled context transformer"},{"key":"7366_CR129","unstructured":"Hudson D, Zitnick L (2021) Generative adversial transformers. In: International conference on machine learning, pp 4487\u20134499"},{"key":"7366_CR130","unstructured":"Radford A et al (2018) Improving language understanding by generative pre-training. Technical Report, OpenAI"},{"issue":"8","key":"7366_CR131","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford A et al (2019) Language models are unsupervised multitask learners. OpenAI blog 1(8):9","journal-title":"OpenAI blog"},{"key":"7366_CR132","unstructured":"Dehghani M et al (2019) Universal transformers. In: International conference on learning representations"},{"key":"7366_CR133","unstructured":"Parmar N (2018) Image transformer"},{"key":"7366_CR134","doi-asserted-by":"crossref","unstructured":"Dai Z et al (2019) Transformer- XL: attentive language models beyond a fixed-length context. In: Proceedings of the 57th annual meeting of the association for computational linguistics, pp 2978\u20132988","DOI":"10.18653\/v1\/P19-1285"},{"key":"7366_CR135","unstructured":"Parisotto E (2020) Stabilizing transformers for reinforcement learning"},{"key":"7366_CR136","first-page":"2232","volume":"32","author":"X Ma","year":"2019","unstructured":"Ma X et al (2019) A Tensorized Transformer for Language Modeling. Adv Neural Inf Process Syst 32:2232\u20132242","journal-title":"Adv Neural Inf Process Syst"},{"issue":"3","key":"7366_CR137","doi-asserted-by":"publisher","first-page":"1033","DOI":"10.1137\/070690729","volume":"30","author":"L Lathauwer","year":"2008","unstructured":"Lathauwer L (2008) Decompositions of a higher-order tensor in block terms-part ii: definitions and uniqueness. SIAM J Matrix Anal Appl 30(3):1033","journal-title":"SIAM J Matrix Anal Appl"},{"issue":"3","key":"7366_CR138","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1007\/BF02289464","volume":"31","author":"L Tucker","year":"1966","unstructured":"Tucker L (1966) Some mathematical notes on three-mode factor analysis. Psychometrika 31(3):279","journal-title":"Psychometrika"},{"key":"7366_CR139","first-page":"4171","volume":"2019","author":"J Devlin","year":"2019","unstructured":"Devlin J et al (2019) BERT: Pre-training of deep bidirectional transformers for language understanding. Proc of NAACL-HLT 2019:4171\u20134186","journal-title":"Proc of NAACL-HLT"},{"issue":"4","key":"7366_CR140","first-page":"415","volume":"30","author":"W Taylor","year":"1953","unstructured":"Taylor W (1953) Cloze procedure: a new tool for measuring readability. J Bull 30(4):415","journal-title":"J Bull"},{"key":"7366_CR141","doi-asserted-by":"crossref","unstructured":"Clark K et al (2019) What does BERT look at? An analysis of BERT\u2019s attention, arXiv preprint arXiv:1906.04341","DOI":"10.18653\/v1\/W19-4828"},{"key":"7366_CR142","doi-asserted-by":"crossref","unstructured":"Sun S et al (2019) Patient knowledge distillation for BERT model compression. In: Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing, Hong Kong, pp 4323\u20134332","DOI":"10.18653\/v1\/D19-1441"},{"key":"7366_CR143","unstructured":"Wang W et al (2020) MINILM: deep self-attention distillation for task-agnostic compression of pre-trained transformers. Advances in Neural Information Processing Systems, 33"},{"key":"7366_CR144","unstructured":"McCarley J, Chakravarti R, Sil A (2020) Structured pruning of a BERT-based question answering model, arXiv preprint arXiv:1910.06360"},{"key":"7366_CR145","doi-asserted-by":"crossref","unstructured":"Zafrir O et al (2019) Q8 BERT: quantized 8Bit BERT. In: The 5th workshop on energy efficient machine learning and cognitive computing - NeurIPS","DOI":"10.1109\/EMC2-NIPS53020.2019.00016"},{"key":"7366_CR146","doi-asserted-by":"crossref","unstructured":"Joshi M et al (2019) BERT for coreference resolution: baselines and analysis. In: Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing, pp 5803\u20135808","DOI":"10.18653\/v1\/D19-1588"},{"key":"7366_CR147","unstructured":"Gong L et al (2019) Efficient training of BERT by progressively stacking. In: International conference on machine learning, pp 2337\u20132346"},{"key":"7366_CR148","unstructured":"Lan Z et al (2020) ALBERT: a lite BERT for self-supervised learning of language representations. In: International conference on learning representations"},{"key":"7366_CR149","unstructured":"Goyal S et al (2020) Po WER-BERT: accelerating BERT inference via progressive word-vector elimination"},{"key":"7366_CR150","doi-asserted-by":"crossref","unstructured":"Jiao X et al (2019) Tiny BERT: distilling BERT for natural language understanding, arXiv preprint arXiv:1909.10351","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"7366_CR151","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1162\/tacl_a_00300","volume":"8","author":"M Joshi","year":"2020","unstructured":"Joshi M et al (2020) Span BERT: improving pre-training by representing and predicting spans. Trans Assoc Comput Linguist 8:64","journal-title":"Trans Assoc Comput Linguist"},{"key":"7366_CR152","unstructured":"Liu Y et al (2019) Ro BERTa: a robustly optimized BERT pretraining approach, arXiv preprint arXiv:1907.11692"},{"key":"7366_CR153","unstructured":"He P et al (2021) DeBERTa: decoding-enhanced BERT with disentangled attention. In: International conference on learning representations"},{"key":"7366_CR154","unstructured":"Sanh V et al (2019) DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. In: The 5th workshop on energy efficient machine learning and cognitive computing\u2014NeurIPS"},{"key":"7366_CR155","unstructured":"Wang W et al (2020) Struct BERT: incorporating language structures into pre-training for deep language understanding. In: International conference on learning representations"},{"key":"7366_CR156","first-page":"8815","volume":"34","author":"S Shen","year":"2020","unstructured":"Shen S et al (2020) Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT. AAAI Conf Artif Intell 34:8815","journal-title":"AAAI Conf Artif Intell"},{"issue":"4","key":"7366_CR157","doi-asserted-by":"crossref","first-page":"1234","DOI":"10.1093\/bioinformatics\/btz682","volume":"36","author":"J Lee","year":"2020","unstructured":"Lee J et al (2020) Bio BERT: a pre-trained biomedical language representation model for biomedical text mining. Bioinformatics 36(4):1234","journal-title":"Bioinformatics"},{"key":"7366_CR158","first-page":"453","volume":"35","author":"P Prakash","year":"2021","unstructured":"Prakash P et al (2021) Rare BERT: transformer architecture for rare disease patient identification using administrative claims. AAAI Conf Artif Intell 35:453","journal-title":"AAAI Conf Artif Intell"},{"key":"7366_CR159","unstructured":"Wu Z et al (2020) Lite transformer with long-short range attention. In: International conference on learning representations UK"},{"key":"7366_CR160","unstructured":"Mehta S et al (2021) DeLighT: deep and light-weight transformer. In: International conference on learning representations"},{"key":"7366_CR161","unstructured":"Tay Y et al (2021) HyperGrid transformers: towards a single model for multiple tasks. In: International conference on learning representations"},{"key":"7366_CR162","unstructured":"Yun S et al (2018) Graph transformer networks. In: International conference on learning representations"},{"key":"7366_CR163","unstructured":"Rong Y et al (2020) Self-supervised graph transformer on large-scale molecular data. Advances in Neural Information Processing Systems, 33"},{"key":"7366_CR164","unstructured":"J.\u00a0Yang, et\u00a0al.,(2021) GraphFormers:GNN-nested transformers for representation learning on textual graph. Advances in Neural Information Processing Systems, 34"},{"key":"7366_CR165","unstructured":"ZhaoC et al (2020) Transformer-XH: multi-evidence reasoning with extra hop attention. In: International conference on learning representations"},{"key":"7366_CR166","unstructured":"You R et al (2019) AttentionXML: label tree-based attention-aware deep model for high-performance extreme multi-label text classification. Advances in Neural Information Processing Systems, 32"},{"key":"7366_CR167","unstructured":"Fan X et al (2020) Bayesian attention modules. Advances in Neural Information Processing Systems, 33"},{"key":"7366_CR168","unstructured":"Brunner G et al (2020) On identifiability in transformers. In: International conference on learning representations"},{"key":"7366_CR169","unstructured":"Dosovitskiy A et al (2021) An image is worth $$16 \\times 16$$ words: transformers for image recognition at scale. In: International conference on learning representations"},{"key":"7366_CR170","unstructured":"Katharopoulos A et al (2020) Transformers are RNNs: fast autoregressive transformers with linear attention"},{"issue":"2","key":"7366_CR171","doi-asserted-by":"publisher","first-page":"325","DOI":"10.1016\/0021-9991(87)90140-9","volume":"73","author":"L Greengard","year":"1987","unstructured":"Greengard L, Rokhlin V (1987) A fast algorithm for particle simulations. J Comput Phys 73(2):325","journal-title":"J Comput Phys"},{"key":"7366_CR172","unstructured":"Nguyen T et al (2021) FMMformer: efficient and flexible transformer via decomposed near-field and far-field attention. Advances in Neural Information Processing Systems, 34"},{"key":"7366_CR173","unstructured":"Kitaev N, Kaiser L, Levskaya A (2020) Reformer: the efficient transformer"},{"key":"7366_CR174","unstructured":"Lee J et al (2019) Set transformer: a framework for attention-based permutation-invariant neural networks. In: International conference on machine learning pp 3744\u20133753"},{"key":"7366_CR175","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1162\/tacl_a_00353","volume":"9","author":"A Roy","year":"2020","unstructured":"Roy A et al (2020) Efficient content-based sparse attention with routing transformers. Trans Assoc Comput Linguist 9:53\u201368","journal-title":"Trans Assoc Comput Linguist"},{"key":"7366_CR176","unstructured":"Child R et al (2019) Generating long sequences with sparse transformers, arXiv preprint arXiv:1904.10509"},{"key":"7366_CR177","doi-asserted-by":"crossref","unstructured":"Correia G, Niculae V, Martins A (2019) Adaptively sparse transformers. In: Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing pp 2174\u20132184","DOI":"10.18653\/v1\/D19-1223"},{"key":"7366_CR178","unstructured":"Peng H et al (2021) Random feature attention. In: International conference on learning representations UK"},{"key":"7366_CR179","unstructured":"Chen Y et al (2021) Skyformer: remodel self-attention with Gaussian kernel and Nystr\u00f6m method. Advances in Neural Information Processing Systems, 34"},{"key":"7366_CR180","unstructured":"Zaheer M et al (2020) Big bird: transformers for longer sequences. Advances in Neural Information Processing Systems, 33"},{"key":"7366_CR181","unstructured":"Huang CZ et al (2019) Music transformer: generating music with long-term structure. In: International conference on learning representations UK"},{"key":"7366_CR182","unstructured":"Lu J et al (2021) SOFT: softmax-free transformer with linear complexity. Advances in Neural Information Processing Systems, 34"},{"key":"7366_CR183","doi-asserted-by":"crossref","unstructured":"Pan Z et al (2021) Scalable vision transformers with hierarchical pooling. In: Proceedings of the IEEE\/cvf international conference on computer vision, pp 377\u2013386","DOI":"10.1109\/ICCV48922.2021.00043"},{"key":"7366_CR184","unstructured":"Zhu C et al (2021) Long-short transformer: efficient transformers for language and vision. Advances in Neural Information Processing Systems, 34"},{"key":"7366_CR185","unstructured":"Jaegle A et al (2021) Perceiver: general perception with iterative attention. In: International conference on machine learning, pp 4651\u20134664"},{"key":"7366_CR186","unstructured":"Choromanski K et al (2021) Rethinking attention with performers. In: International conference on learning representations"},{"key":"7366_CR187","unstructured":"El-Nouby A et al. (2021) XCiT: cross-covariance image transformers. Advances in neural information processing systems, 34"},{"key":"7366_CR188","unstructured":"Yu Q et al (2021) Glance-and-gaze vision transformer. Advances in Neural Information Processing Systems, 34"},{"key":"7366_CR189","unstructured":"Zeng Z et al (2021) You only sample (almost) once: linear cost self-attention via Bernoulli sampling. In: International conference on machine learning, pp 12,321\u201312,332"},{"key":"7366_CR190","unstructured":"Shen Z et al (2021) Efficient attention: attention with linear complexities. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision, pp 3531\u20133539"},{"key":"7366_CR191","doi-asserted-by":"crossref","unstructured":"Luo S et al (2021) Stable, fast and accurate: kernelized attention with relative positional encoding. Advances in Neural Information Processing Systems, 34","DOI":"10.1007\/978-3-030-92273-3_1"},{"key":"7366_CR192","unstructured":"Ma X et al (2021) Luna: linear unified nested attention. Advances in Neural Information Processing Systems, 34"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-022-07366-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-022-07366-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-022-07366-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,6]],"date-time":"2023-02-06T03:53:20Z","timestamp":1675655600000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-022-07366-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,25]]},"references-count":192,"journal-issue":{"issue":"16","published-print":{"date-parts":[[2022,8]]}},"alternative-id":["7366"],"URL":"https:\/\/doi.org\/10.1007\/s00521-022-07366-3","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,5,25]]},"assertion":[{"value":"22 July 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 April 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 May 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":"The authors declare that there is no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}