{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T08:07:17Z","timestamp":1764144437083,"version":"3.46.0"},"reference-count":119,"publisher":"Springer Science and Business Media LLC","issue":"16","license":[{"start":{"date-parts":[[2025,10,20]],"date-time":"2025-10-20T00:00:00Z","timestamp":1760918400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,20]],"date-time":"2025-10-20T00:00:00Z","timestamp":1760918400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100003593","name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003593","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Funda\u00e7\u00e3o de Amparo a Ci\u00eancia e Tecnologia do Estado de Pernambuco"},{"DOI":"10.13039\/501100002322","name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002322","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001807","name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de Ss\u0303o Paulo","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001807","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Ericsson Telecommunications Inc., Brazil"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1007\/s10489-025-06916-1","type":"journal-article","created":{"date-parts":[[2025,10,20]],"date-time":"2025-10-20T14:36:54Z","timestamp":1760971014000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing computational efficiency in digital twins: a survey of techniques and challenges for fast inference"],"prefix":"10.1007","volume":"55","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7927-8472","authenticated-orcid":false,"given":"Marrone","family":"Dantas","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Miguel LPC","family":"Silva","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Assis T.","family":"de Oliveira Filho","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Diego","family":"de Freitas Bezerra","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eduardo","family":"Freitas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pedro R. X.","family":"do Carmo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Djamel","family":"Sadok","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Judith","family":"Kelner","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ricardo","family":"Souza","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,10,20]]},"reference":[{"key":"6916_CR1","doi-asserted-by":"publisher","unstructured":"Mylonas G, Kalogeras AP, Kalogeras G, Anagnostopoulos C, Alexakos C, Munoz L (2021) Digital twins from smart manufacturing to smart cities: a survey. IEEE Access PP:1\u20131. https:\/\/doi.org\/10.1109\/ACCESS.2021.3120843","DOI":"10.1109\/ACCESS.2021.3120843"},{"key":"6916_CR2","doi-asserted-by":"publisher","first-page":"372","DOI":"10.1016\/j.jmsy.2022.06.015","volume":"64","author":"F Tao","year":"2022","unstructured":"Tao F, Xiao B, Qi Q, Cheng J, Ji P (2022) Digital twin modeling. J Manuf Syst 64:372\u2013389. https:\/\/doi.org\/10.1016\/j.jmsy.2022.06.015","journal-title":"J Manuf Syst"},{"key":"6916_CR3","doi-asserted-by":"publisher","unstructured":"Tekinerdogan B (2023) On the notion of digital twins: a modeling perspective. Systems 11(1). https:\/\/doi.org\/10.3390\/systems11010015","DOI":"10.3390\/systems11010015"},{"issue":"4","key":"6916_CR4","doi-asserted-by":"publisher","first-page":"14534","DOI":"10.1016\/j.heliyon.2023.e14534","volume":"9","author":"D Zhong","year":"2023","unstructured":"Zhong D, Xia Z, Zhu Y, Duan J (2023) Overview of predictive maintenance based on digital twin technology. Heliyon 9(4):14534. https:\/\/doi.org\/10.1016\/j.heliyon.2023.e14534","journal-title":"Heliyon"},{"key":"6916_CR5","doi-asserted-by":"publisher","first-page":"100445","DOI":"10.1016\/j.jii.2023.100445","volume":"33","author":"I Petri","year":"2023","unstructured":"Petri I, Rezgui Y, Ghoroghi A, Alzahrani A (2023) Digital twins for performance management in the built environment. J Ind Inf Integr 33:100445. https:\/\/doi.org\/10.1016\/j.jii.2023.100445","journal-title":"J Ind Inf Integr"},{"key":"6916_CR6","doi-asserted-by":"publisher","unstructured":"Henson CM, Decker NI, Huang Q (2021) A digital twin strategy for major failure detection in fused deposition modeling processes. Procedia Manuf 53:359\u2013367. https:\/\/doi.org\/10.1016\/j.promfg.2021.06.039. 49th SME North American Manufacturing Research Conference (NAMRC 49, 2021)","DOI":"10.1016\/j.promfg.2021.06.039"},{"key":"6916_CR7","doi-asserted-by":"publisher","unstructured":"Caprari G, Castelli G, Montuori M, Camardelli M, Malvezzi R (2022) Digital twin for urban planning in the green deal era: a state of the art and future perspectives. Sustainability 14(10). https:\/\/doi.org\/10.3390\/su14106263","DOI":"10.3390\/su14106263"},{"key":"6916_CR8","doi-asserted-by":"publisher","unstructured":"Alfrink, M., Ro\u00dfmann, J.: Real-time spatio-temporal databases: Bridging the gap between experimentable digital twins and databases. In: 2022 Winter Simulation Conference (WSC). IEEE, pp 2888\u20132899 (2022). https:\/\/doi.org\/10.1109\/WSC57314.2022.10015268","DOI":"10.1109\/WSC57314.2022.10015268"},{"key":"6916_CR9","doi-asserted-by":"publisher","unstructured":"Shi K, Qian K, Yu H (2022) Visual human localization and safety monitoring in a digital twin of workspace. In: 2022 41st Chinese Control Conference (CCC), pp 6117\u20136121. https:\/\/doi.org\/10.23919\/CCC55666.2022.9902056","DOI":"10.23919\/CCC55666.2022.9902056"},{"key":"6916_CR10","doi-asserted-by":"publisher","first-page":"103987","DOI":"10.1016\/j.compind.2023.103987","volume":"151","author":"M Perno","year":"2023","unstructured":"Perno M, Hvam L, Haug A (2023) A machine learning digital twin approach for critical process parameter prediction in a catalyst manufacturing line. Comput Ind 151:103987. https:\/\/doi.org\/10.1016\/j.compind.2023.103987","journal-title":"Comput Ind"},{"key":"6916_CR11","doi-asserted-by":"publisher","unstructured":"Zhang L, Yan Y, Hu Y, Ren W (2022) Reinforcement learning and digital twin-based real-time scheduling method in intelligent manufacturing systems. IFAC-PapersOnLine 55(10):359\u2013364. https:\/\/doi.org\/10.1016\/j.ifacol.2022.09.413. 10th IFAC Conference on Manufacturing Modelling, Management and Control MIM 2022","DOI":"10.1016\/j.ifacol.2022.09.413"},{"issue":"4","key":"6916_CR12","first-page":"789","volume":"36","author":"AB Smith","year":"2022","unstructured":"Smith AB, Johnson CD (2022) Convergence of machine learning and digital twin technologies in environmental modeling. J Adv Comput Intell Inform 36(4):789\u2013798","journal-title":"J Adv Comput Intell Inform"},{"key":"6916_CR13","doi-asserted-by":"publisher","unstructured":"Ricondo I, Porto A, Ugarte M (2021) A digital twin framework for the simulation and optimization of production systems. Procedia CIRP 104:762\u2013767. https:\/\/doi.org\/10.1016\/j.procir.2021.11.128. 54th CIRP CMS 2021 - Towards Digitalized Manufacturing 4.0","DOI":"10.1016\/j.procir.2021.11.128"},{"key":"6916_CR14","unstructured":"Han S, Pool J, Tran J, Dally W (2016) Learning both weights and connections for efficient neural networks. In: Proceedings of the 28th international conference on neural information processing systems - Volume 1, pp 1135\u20131143"},{"key":"6916_CR15","doi-asserted-by":"crossref","unstructured":"Liang T, Glossner J, Wang L, Shi S (2021) Pruning and quantization for deep neural network acceleration: a survey. arXiv:2101.09671","DOI":"10.1016\/j.neucom.2021.07.045"},{"key":"6916_CR16","doi-asserted-by":"publisher","unstructured":"Caiza G, Sanz R (2022) Digital twin for monitoring an industrial process using augmented reality. In: 2022 17th Iberian Conference on Information Systems and Technologies (CISTI). IEEE, pp 1\u20135. https:\/\/doi.org\/10.23919\/cisti54924.2022.9820356","DOI":"10.23919\/cisti54924.2022.9820356"},{"issue":"24","key":"6916_CR17","doi-asserted-by":"publisher","first-page":"12741","DOI":"10.3390\/app122412741","volume":"12","author":"L Luka\u010d","year":"2022","unstructured":"Luka\u010d L, Fister I, Fister IJ (2022) Digital twin in sport: from an idea to realization. Appl Sci 12(24):12741. https:\/\/doi.org\/10.3390\/app122412741","journal-title":"Appl Sci"},{"key":"6916_CR18","doi-asserted-by":"publisher","unstructured":"Grieves M (2005) Product lifecycle management: the new paradigm for enterprises. Int J Prod Dev 2. https:\/\/doi.org\/10.1504\/IJPD.2005.006669","DOI":"10.1504\/IJPD.2005.006669"},{"key":"6916_CR19","doi-asserted-by":"publisher","unstructured":"V\u00e4\u00e4n\u00e4nen K, Saarinen P, W\u00e4ljas M, H\u00e4nnik\u00e4inen M, Orsila H, Kiukkonen N (2010) User experience of social ad hoc networking: findings from a large-scale field trial of twin, p. 10. https:\/\/doi.org\/10.1145\/1899475.1899485","DOI":"10.1145\/1899475.1899485"},{"key":"6916_CR20","doi-asserted-by":"publisher","first-page":"359","DOI":"10.3390\/biomimetics8040359","volume":"8","author":"T Sigawi","year":"2023","unstructured":"Sigawi T, Ilan Y (2023) Using constrained-disorder principle-based systems to improve the performance of digital twins in biological systems. Biomimetics 8:359. https:\/\/doi.org\/10.3390\/biomimetics8040359","journal-title":"Biomimetics"},{"key":"6916_CR21","doi-asserted-by":"publisher","first-page":"2255","DOI":"10.1109\/COMST.2022.3208773","volume":"24","author":"S Mihai","year":"2022","unstructured":"Mihai S et al (2022) Digital twins: a survey on enabling technologies, challenges, trends and future prospects. IEEE Commun Surv Tutor 24:2255\u20132291. https:\/\/doi.org\/10.1109\/COMST.2022.3208773","journal-title":"IEEE Commun Surv Tutor"},{"key":"6916_CR22","doi-asserted-by":"publisher","first-page":"609","DOI":"10.1080\/19401493.2023.2187463","volume":"16","author":"R Ward","year":"2023","unstructured":"Ward R, Choudary R, Singh MJ et al (2023) The challenges of using live-streamed data in a predictive digital twin. J Build Perform Simul 16:609\u2013630. https:\/\/doi.org\/10.1080\/19401493.2023.2187463","journal-title":"J Build Perform Simul"},{"key":"6916_CR23","unstructured":"How to Secure Digital Twin Technology in Your Data Center \u2014 datacenterknowledge.com. https:\/\/www.datacenterknowledge.com\/security\/how-secure-digital-twin-technology-your-data-center. Accessed 04 Jan 2024"},{"key":"6916_CR24","doi-asserted-by":"publisher","unstructured":"Issa R, Hamad MS, Abdel-Geliel M (2023) Digital twin of wind turbine based on microsoft\u00ae azure iot platform. IEEE Conference on Power Electronics and Renewable Energy (CPERE), 1\u20138. https:\/\/doi.org\/10.1109\/CPERE56564.2023.10119576","DOI":"10.1109\/CPERE56564.2023.10119576"},{"key":"6916_CR25","doi-asserted-by":"crossref","unstructured":"Chakraborty SL, Adhikari S (2020) Machine learning based digital twin for dynamical systems with multiple time-scales. arXiv:2005.05862","DOI":"10.1016\/j.compstruc.2020.106410"},{"key":"6916_CR26","doi-asserted-by":"publisher","first-page":"110145","DOI":"10.1016\/j.cie.2024.110145","volume":"191","author":"RR Corsini","year":"2024","unstructured":"Corsini RR, Costa A, Fichera S, Framinan JM (2024) Digital twin model with machine learning and optimization for resilient production-distribution systems under disruptions. Comput Ind Eng 191:110145. https:\/\/doi.org\/10.1016\/j.cie.2024.110145","journal-title":"Comput Ind Eng"},{"issue":"4","key":"6916_CR27","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1162\/neco.1989.1.4.541","volume":"1","author":"Y LeCun","year":"1989","unstructured":"LeCun Y, Boser B, Denker JS, Henderson D, Howard RE, Hubbard W, Jackel LD (1989) Backpropagation applied to handwritten zip code recognition. Neural Comput 1(4):541\u2013551","journal-title":"Neural Comput"},{"key":"6916_CR28","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, vol 25, pp 1097\u20131105"},{"issue":"1","key":"6916_CR29","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1186\/s40537-021-00444-8","volume":"8","author":"L Alzubaidi","year":"2021","unstructured":"Alzubaidi L, Zhang J, Humaidi AJ, Al-Dujaili A, Duan Y, Al-Shamma O, Santamar\u00eda J, Fadhel MA, Al-Amidie M, Farhan L (2021) Review of deep learning: concepts, cnn architectures, challenges, applications, future directions. J Big Data 8(1):53. https:\/\/doi.org\/10.1186\/s40537-021-00444-8","journal-title":"J Big Data"},{"key":"6916_CR30","doi-asserted-by":"crossref","unstructured":"Jouppi NP, Young C, Patil N, Patterson D, Agrawal G, Bajwa R, Bates S, Bhatia S, Boden N, Borchers A et al (2017) In-datacenter performance analysis of a tensor processing unit. In: Proceedings of the 44th annual international symposium on computer architecture. ACM, pp 1\u201312","DOI":"10.1145\/3079856.3080246"},{"key":"6916_CR31","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, Li L-J, Li K, Fei-Fei L (2009) Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on computer vision and pattern recognition. IEEE, pp 248\u2013255","DOI":"10.1109\/CVPR.2009.5206848"},{"issue":"3","key":"6916_CR32","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, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M et al (2015) Imagenet large scale visual recognition challenge. Int J Comput Vision 115(3):211\u2013252","journal-title":"Int J Comput Vision"},{"issue":"1","key":"6916_CR33","first-page":"1","volume":"21","author":"T Poggio","year":"2020","unstructured":"Poggio T, Banburski A, Liao Q (2020) Theory of deep learning iii: explaining the non-overfitting puzzle. J Mach Learn Res 21(1):1\u201340","journal-title":"J Mach Learn Res"},{"key":"6916_CR34","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"6916_CR35","unstructured":"Tan M, Le Q (2019) Efficientnet: rethinking model scaling for convolutional neural networks. In: International conference on machine learning. PMLR, pp 6105\u20136114"},{"key":"6916_CR36","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly S et al (2020) An image is worth 16x16 words: transformers for image recognition at scale. arXiv:2010.11929"},{"key":"6916_CR37","doi-asserted-by":"publisher","unstructured":"Ajit A, Acharya K, Samanta A (2020) A review of convolutional neural networks. In: 2020 International Conference on Emerging Trends in Information Technology and Engineering (ic-ETITE), pp 1\u20135. https:\/\/doi.org\/10.1109\/ic-ETITE47903.2020.049","DOI":"10.1109\/ic-ETITE47903.2020.049"},{"key":"6916_CR38","doi-asserted-by":"crossref","unstructured":"Rodrigues IR, Barbosa G, Oliveira Filho A, Cani C, Sadok DH, Kelner J, Souza R, Marquezini MV, Lins S (2021) A new mechanism for collision detection in human-robot collaboration using deep learning techniques. J Control Autom Electr Syst 1\u201313","DOI":"10.1007\/s40313-021-00829-3"},{"issue":"4","key":"6916_CR39","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10846-022-01701-5","volume":"105","author":"G Barbosa","year":"2022","unstructured":"Barbosa G, Ledebour C, Oliveira Filho AT, Rodrigues IR, Sadok D, Kelner J, Souza R (2022) Hosa: an end-to-end safety system for human-robot interaction. J Intell Robot Syst 105(4):1\u201324","journal-title":"J Intell Robot Syst"},{"key":"6916_CR40","doi-asserted-by":"publisher","unstructured":"Fukui S, Yu J, Hashimoto M (2019) Distilling knowledge for non-neural networks. 2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), 1411\u20131416. https:\/\/doi.org\/10.1109\/APSIPAASC47483.2019.9023120","DOI":"10.1109\/APSIPAASC47483.2019.9023120"},{"key":"6916_CR41","doi-asserted-by":"publisher","unstructured":"Dong D, Liu J, Wang X, Gong W, Qin A, Li X, Yu D, Valduriez P, Dou D (2021) Elastic deep learning using knowledge distillation with heterogeneous computing resources, pp 116\u2013128. https:\/\/doi.org\/10.1007\/978-3-031-06156-1_10","DOI":"10.1007\/978-3-031-06156-1_10"},{"key":"6916_CR42","first-page":"102927","volume":"175","author":"A Kumar","year":"2021","unstructured":"Kumar A et al (2021) Efficient healthcare data processing through cnn split computing. J Netw Comput Appl 175:102927","journal-title":"J Netw Comput Appl"},{"issue":"2","key":"6916_CR43","first-page":"1234","volume":"71","author":"B Zhao","year":"2022","unstructured":"Zhao B et al (2022) Real-time object detection in autonomous driving using a peer-to-peer network. IEEE Trans Veh Technol 71(2):1234\u20131247","journal-title":"IEEE Trans Veh Technol"},{"issue":"4","key":"6916_CR44","first-page":"1234","volume":"29","author":"D Johnson","year":"2021","unstructured":"Johnson D et al (2021) Enhancing real-time video processing in edge computing with data parallelism. J Netw Syst Manage 29(4):1234\u20131256","journal-title":"J Netw Syst Manage"},{"key":"6916_CR45","unstructured":"Johnson D et al (2021) Efficiency in large-scale neural networks through layer splitting. J Parallel Comput"},{"key":"6916_CR46","unstructured":"Smith R et al (2022) Advances in parameter sharing techniques for distributed machine learning. IEEE Trans Neural Netw Learn Syst"},{"issue":"19","key":"6916_CR47","doi-asserted-by":"publisher","first-page":"22818","DOI":"10.1007\/s10489-023-04730-1","volume":"53","author":"L Meneghetti","year":"2023","unstructured":"Meneghetti L, Demo N, Rozza G (2023) A dimensionality reduction approach for convolutional neural networks. Appl Intell 53(19):22818\u201322833. https:\/\/doi.org\/10.1007\/s10489-023-04730-1","journal-title":"Appl Intell"},{"key":"6916_CR48","unstructured":"Malekhosseini E, Hajabdollahi M, Karimi N, Samavi S, Shirani S (2020) Splitting convolutional neural network structures for efficient inference. arXiv:2002.03302"},{"key":"6916_CR49","doi-asserted-by":"crossref","unstructured":"Teerapittayanon S, McDanel B, Kung H-T (2016) Branchynet: fast inference via early exiting from deep neural networks. In: 2016 23rd International Conference on Pattern Recognition (ICPR). IEEE, pp 2464\u20132469","DOI":"10.1109\/ICPR.2016.7900006"},{"key":"6916_CR50","doi-asserted-by":"publisher","unstructured":"Leontiadis I, Laskaridis S, Venieris SI, Lane ND (2021) It\u2019s always personal: using early exits for efficient on-device cnn personalisation. In: Proceedings of the 22nd international workshop on mobile computing systems and applications. HotMobile \u201921. Association for Computing Machinery, New York, NY, USA, pp 15\u201321. https:\/\/doi.org\/10.1145\/3446382.3448359","DOI":"10.1145\/3446382.3448359"},{"key":"6916_CR51","doi-asserted-by":"crossref","unstructured":"Phuong M, Lampert CH (2019) Distillation-based training for multi-exit architectures. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 1355\u20131364","DOI":"10.1109\/ICCV.2019.00144"},{"key":"6916_CR52","unstructured":"Huang G, Chen D, Li T, Wu F, Maaten L, Weinberger KQ (2018) Multi-scale dense networks for resource efficient image classification. In: Proceedings of the International Conference on Learning Representations (ICLR)"},{"key":"6916_CR53","doi-asserted-by":"crossref","unstructured":"Huang G, Liu Z, Van Der\u00a0Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. Proceedings of the IEEE conference on computer vision and pattern recognition, 4700\u20134708","DOI":"10.1109\/CVPR.2017.243"},{"key":"6916_CR54","doi-asserted-by":"crossref","unstructured":"Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. Proceedings of the IEEE conference on computer vision and pattern recognition, 1\u20139","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"6916_CR55","doi-asserted-by":"crossref","unstructured":"Bakhtiarnia A, Zhang Q, Iosifidis A (2021) Improving the accuracy of early exits in multi-exit architectures via curriculum learning. 2021 International Joint Conference on Neural Networks (IJCNN), 1\u20138","DOI":"10.1109\/IJCNN52387.2021.9533875"},{"key":"6916_CR56","unstructured":"Bahdanau D, Cho K, Bengio Y (2014) Neural machine translation by jointly learning to align and translate. In: International conference on learning representations"},{"key":"6916_CR57","unstructured":"Lee C-Y, Xie S, Gallagher P, Zhang Z, Tu Z (2015) Deeply-supervised nets. Artificial Intelligence and Statistics, 562\u2013570"},{"issue":"8","key":"6916_CR58","doi-asserted-by":"publisher","first-page":"1771","DOI":"10.1162\/089976602760128018","volume":"14","author":"GE Hinton","year":"2002","unstructured":"Hinton GE (2002) Training products of experts by minimizing contrastive divergence. Neural Comput 14(8):1771\u20131800","journal-title":"Neural Comput"},{"key":"6916_CR59","unstructured":"Wang Y, Xu F, Chen P-Y, Xiong Y, Xu C-Z (2020) Adaptive neural networks for efficient inference. Proceedings of the 37th international conference on machine learning"},{"issue":"2","key":"6916_CR60","doi-asserted-by":"publisher","first-page":"239","DOI":"10.1109\/72.80236","volume":"1","author":"E Karnin","year":"1990","unstructured":"Karnin E (1990) A simple procedure for pruning back-propagation trained neural networks. IEEE Trans Neural Networks 1(2):239\u2013242. https:\/\/doi.org\/10.1109\/72.80236","journal-title":"IEEE Trans Neural Networks"},{"key":"6916_CR61","unstructured":"Hassibi B, Stork DG (1992) Second order derivatives for network pruning: optimal brain surgeon. In: Proceedings of the 5th International Conference on Neural Information Processing Systems. NIPS\u201992, pp. 164\u2013171. Morgan Kaufmann Publishers Inc., San Francisco, CA, USA"},{"key":"6916_CR62","doi-asserted-by":"crossref","unstructured":"Wang H, Fu Y (2023) Trainability preserving neural pruning","DOI":"10.1155\/2023\/9983781"},{"key":"6916_CR63","unstructured":"Cheng H, Zhang M, Shi JQ (2023) A survey on deep neural network pruning-taxonomy, comparison, analysis, and recommendations. arXiv:2308.06767"},{"key":"6916_CR64","doi-asserted-by":"crossref","unstructured":"Lagunas F, Charlaix E, Sanh V, Rush AM (2021) Block pruning for faster transformers","DOI":"10.18653\/v1\/2021.emnlp-main.829"},{"key":"6916_CR65","unstructured":"Laurent C, Ballas C, George T, Ballas N, Vincent P (2020) Revisiting loss modelling for unstructured pruning"},{"key":"6916_CR66","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3277689","author":"L Yang","year":"2023","unstructured":"Yang L, Gu S, Shen C, Zhao X, Hu Q (2023) Low-rank guided pruning for filter pruning in neural networks. IEEE Trans Circuits Syst Video Technol. https:\/\/doi.org\/10.1109\/TCSVT.2023.3277689","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"6916_CR67","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3189496","author":"N Kim","year":"2022","unstructured":"Kim N, Kim H (2022) Fp-agl: filter pruning via adaptive gradient learning. IEEE Trans Multimedia. https:\/\/doi.org\/10.1109\/TMM.2022.3189496","journal-title":"IEEE Trans Multimedia"},{"key":"6916_CR68","doi-asserted-by":"publisher","unstructured":"He Y, Ding Y, Liu P, Zhu L, Zhang H, Yang Y (2020) Learning filter pruning criteria for deep convolutional neural networks acceleration. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00208","DOI":"10.1109\/CVPR42600.2020.00208"},{"key":"6916_CR69","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3292152","author":"Y Chen","year":"2023","unstructured":"Chen Y, Li R, Li W, Wang J, Li R-X (2023) Three-stage global channel pruning for deep neural networks. IEEE Trans Neural Netw Learn Syst. https:\/\/doi.org\/10.1109\/TNNLS.2023.3292152","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"6916_CR70","doi-asserted-by":"publisher","unstructured":"Xie W, Feng X (2023) Automatic channel pruning for neural networks using sparrow search algorithm. In: SPIE. https:\/\/doi.org\/10.1117\/12.2660854","DOI":"10.1117\/12.2660854"},{"key":"6916_CR71","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3165123","author":"Y-J Zheng","year":"2022","unstructured":"Zheng Y-J, Chen S, Ding CHQ, Luo B (2022) Differentiable network channel pruning for model compression. IEEE Trans Neural Netw Learn Syst. https:\/\/doi.org\/10.1109\/TNNLS.2022.3165123","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"6916_CR72","doi-asserted-by":"publisher","unstructured":"Lazarevich I, Kozlov A, Malinin N (2021) Data-free neural network pruning via parameter similarity. In: IEEE International Conference on Computer Vision Workshops (ICCVW). https:\/\/doi.org\/10.1109\/ICCVW54120.2021.00094","DOI":"10.1109\/ICCVW54120.2021.00094"},{"key":"6916_CR73","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2021edp7096","author":"K Kamma","year":"2022","unstructured":"Kamma K, Inoue S, Wada T (2022) Layer-wise pruning for convolutional neural networks using pruning ratio optimizer. IEICE Trans Inf Syst. https:\/\/doi.org\/10.1587\/transinf.2021edp7096","journal-title":"IEICE Trans Inf Syst"},{"key":"6916_CR74","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/8039281","author":"H Li","year":"2022","unstructured":"Li H, Yue X, Wang Z, Chai Z, Wang W, Tomiyama H, Meng L (2022) Layer-wise refined pruning for deep neural networks. Complexity. https:\/\/doi.org\/10.1155\/2022\/8039281","journal-title":"Complexity"},{"key":"6916_CR75","doi-asserted-by":"publisher","unstructured":"Ge H, Zhou T, Huang C, Li Q, Song X, Wang S, Ma S, Cheng M (2022) Random pruning for neural network compression. In: IEEE International conference on natural language processing and knowledge engineering (NLP-KE). https:\/\/doi.org\/10.1109\/ICNLP55136.2022.00089","DOI":"10.1109\/ICNLP55136.2022.00089"},{"key":"6916_CR76","unstructured":"Lee J, Park S, Mo S, Ahn S, Shin J (2020) Layer-adaptive magnitude-based pruning using a novel importance score. arXiv:2010.07611"},{"key":"6916_CR77","unstructured":"Park S, Lee J, Mo S, Shin J (2020) Lookahead pruning for convolutional neural networks. arXiv:2002.04809"},{"key":"6916_CR78","unstructured":"Han S, Pool J, Tran J, Dally W (2015) Learning both weights and connections for efficient neural network. Adv Neural Inf Process Syst 28"},{"key":"6916_CR79","unstructured":"Li H, Kadav A, Durdanovic I, Samet H, Graf HP (2016) Pruning filters for efficient convnets. In: 5th International Conference on Learning Representations, ICLR 2017"},{"key":"6916_CR80","unstructured":"Dantas MSM, Rodrigues IR, Filho ATO, Barbosa G, Bezerra D, Sadok DFH, Kelner J, Marquezini M, Silva R (2022) FCN-Pose: A pruned and quantized CNN for robot pose estimation for constrained devices"},{"key":"6916_CR81","first-page":"598","volume":"2","author":"Y LeCun","year":"1990","unstructured":"LeCun Y, Denker JS, Solla SA (1990) Optimal brain damage. Adv Neural Inf Process Syst 2:598\u2013605","journal-title":"Adv Neural Inf Process Syst"},{"key":"6916_CR82","unstructured":"Simonyan K, Vedaldi A, Zisserman A (2013) Deep inside convolutional networks: visualising image classification models and saliency maps. In: Workshop at international conference on learning representations"},{"key":"6916_CR83","doi-asserted-by":"crossref","unstructured":"Molchanov P, Mallya A, Tyree S, Frosio I, Kautz J (2019) Importance estimation for neural network pruning. Proceedings of the IEEE conference on computer vision and pattern recognition, 11264\u201311272","DOI":"10.1109\/CVPR.2019.01152"},{"key":"6916_CR84","unstructured":"Michel P, Levy O, Neubig G (2019) Are sixteen heads really better than one? In: Advances in neural information processing systems, vol 32"},{"key":"6916_CR85","unstructured":"Frankle J, Carbin M (2018) The lottery ticket hypothesis: Finding sparse, trainable neural networks. In: International conference on learning representations. https:\/\/openreview.net\/forum?id=rJl-b3RcF7"},{"key":"6916_CR86","unstructured":"Han S, Mao H, Dally WJ (2015) Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. International Conference on Learning Representations"},{"key":"6916_CR87","unstructured":"He Y, Lin J, Liu Z, Wang H, Li L-J, Han S (2018) Automl for model compression. arXiv:1802.03494"},{"key":"6916_CR88","doi-asserted-by":"publisher","unstructured":"Real E, Aggarwal A, Huang Y, Le QV (2019) Regularized evolution for image classifier architecture search. In: Proceedings of the AAAI conference on artificial intelligence, vol 33, pp 4780\u20134789. https:\/\/doi.org\/10.1609\/aaai.v33i01.33014780","DOI":"10.1609\/aaai.v33i01.33014780"},{"key":"6916_CR89","unstructured":"Zhu M, Gupta S (2018) To prune, or not to prune: exploring the efficacy of pruning for model compression. In: 6th International conference on learning representations, ICLR 2018 - Workshop Track Proceedings. https:\/\/openreview.net\/forum?id=Sy1iIDkPM"},{"key":"6916_CR90","doi-asserted-by":"publisher","unstructured":"Liu Z, Mu H, Zhang X, Guo Z, Yang X, Cheng K-T, Sun J (2019) Metapruning: Meta learning for automatic neural network channel pruning. In: Proceedings of the IEEE international conference on computer vision, pp 3296\u20133305. https:\/\/doi.org\/10.1109\/ICCV.2019.00339","DOI":"10.1109\/ICCV.2019.00339"},{"key":"6916_CR91","unstructured":"Hinton G, Vinyals O, Dean J (2015) Distilling the knowledge in a neural network"},{"key":"6916_CR92","doi-asserted-by":"publisher","first-page":"474","DOI":"10.7717\/peerj-cs.474","volume":"7","author":"A Alkhulaifi","year":"2021","unstructured":"Alkhulaifi A, Ahmad I, Alsahli F (2021) Knowledge distillation in deep learning and its applications. PeerJ Comput Sci 7:474. https:\/\/doi.org\/10.7717\/peerj-cs.474","journal-title":"PeerJ Comput Sci"},{"key":"6916_CR93","doi-asserted-by":"crossref","unstructured":"Kim T, Oh J, Kim N, Cho S, Yun S-Y (2021) Comparing kullback-leibler divergence and mean squared error loss in knowledge distillation. In: IJCAI","DOI":"10.24963\/ijcai.2021\/362"},{"key":"6916_CR94","doi-asserted-by":"publisher","first-page":"5026","DOI":"10.1109\/TPAMI.2021.3085525","volume":"44","author":"P Liu","year":"2021","unstructured":"Liu P, Lyu M, King I, Xu J (2021) Learning by distillation: a self-supervised learning framework for optical flow estimation. IEEE Trans Pattern Anal Mach Intell 44:5026\u20135041. https:\/\/doi.org\/10.1109\/TPAMI.2021.3085525","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"6916_CR95","doi-asserted-by":"publisher","unstructured":"Alkhulaifi A, Alsahli F, Ahmad I (2020) Knowledge distillation in deep learning and its applications. PeerJ Comput Sci 7. https:\/\/doi.org\/10.7717\/peerj-cs.474","DOI":"10.7717\/peerj-cs.474"},{"key":"6916_CR96","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3568679","volume":"20","author":"J Gou","year":"2022","unstructured":"Gou J, Sun L, Yu B, Wan S, Tao D (2022) Hierarchical multi-attention transfer for knowledge distillation. ACM Trans Multimed Comput Commun Appl 20:1\u201320. https:\/\/doi.org\/10.1145\/3568679","journal-title":"ACM Trans Multimed Comput Commun Appl"},{"key":"6916_CR97","doi-asserted-by":"publisher","first-page":"2075","DOI":"10.1109\/TCSVT.2022.3222013","volume":"33","author":"T Su","year":"2023","unstructured":"Su T, Liang Q, Zhang J, Yu Z, Xu Z, Wang G, Liu X (2023) Deep cross-layer collaborative learning network for online knowledge distillation. IEEE Trans Circuits Syst Video Technol 33:2075\u20132087. https:\/\/doi.org\/10.1109\/TCSVT.2022.3222013","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"6916_CR98","doi-asserted-by":"publisher","unstructured":"Kwon K, Na, H, Lee H, Kim N (2020) Adaptive knowledge distillation based on entropy. In: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp 7409\u20137413. https:\/\/doi.org\/10.1109\/ICASSP40776.2020.9054698","DOI":"10.1109\/ICASSP40776.2020.9054698"},{"key":"6916_CR99","unstructured":"Mu F, Liang Y, Li Y (2020) Gradients as features for deep representation learning. arXiv:2004.05529"},{"key":"6916_CR100","doi-asserted-by":"publisher","first-page":"1789","DOI":"10.1007\/s11263-021-01453-z","volume":"129","author":"J Gou","year":"2020","unstructured":"Gou J, Yu B, Maybank S, Tao D (2020) Knowledge distillation: a survey. Int J Comput Vis 129:1789\u20131819. https:\/\/doi.org\/10.1007\/s11263-021-01453-z","journal-title":"Int J Comput Vis"},{"key":"6916_CR101","doi-asserted-by":"publisher","unstructured":"Yang Z, Zeng A, Li Z, Zhang T, Yuan C, Li Y (2023) From knowledge distillation to self-knowledge distillation: A unified approach with normalized loss and customized soft labels. arXiv:2303.13005. https:\/\/doi.org\/10.48550\/arXiv.2303.13005","DOI":"10.48550\/arXiv.2303.13005"},{"key":"6916_CR102","doi-asserted-by":"publisher","unstructured":"Yang Z, Li Z, Gong Y, Zhang T, Lao S, Yuan C, Li Y (2022) Rethinking knowledge distillation via cross-entropy. arXiv:2208.10139. https:\/\/doi.org\/10.48550\/arXiv.2208.10139","DOI":"10.48550\/arXiv.2208.10139"},{"key":"6916_CR103","doi-asserted-by":"publisher","unstructured":"Liu H, Yan H, Xia J, Ai Y (2020) Entropy targets for adaptive distillation. Proceedings of the 6th international conference on robotics and artificial intelligence. https:\/\/doi.org\/10.1145\/3449301.3449332","DOI":"10.1145\/3449301.3449332"},{"key":"6916_CR104","doi-asserted-by":"publisher","unstructured":"Hwang D, Sim K, Zhang Y, Strohman T (2022) Comparison of soft and hard target rnn-t distillation for large-scale asr. In: ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). https:\/\/doi.org\/10.1109\/ICASSP49357.2023.10096418","DOI":"10.1109\/ICASSP49357.2023.10096418"},{"key":"6916_CR105","doi-asserted-by":"publisher","unstructured":"Shen Y, Xu L, Yang Y, Li Y, Guo Y (2022) Self-distillation from the last mini-batch for consistency regularization. 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). https:\/\/doi.org\/10.1109\/CVPR52688.2022.01164","DOI":"10.1109\/CVPR52688.2022.01164"},{"key":"6916_CR106","doi-asserted-by":"publisher","unstructured":"Wan Z, Dong Y, Yu Z, Lv H, Lv Z-H (2021) Semi-supervised support vector machine for digital twins based brain image fusion. Front Neurosci 15. https:\/\/doi.org\/10.3389\/fnins.2021.705323","DOI":"10.3389\/fnins.2021.705323"},{"key":"6916_CR107","doi-asserted-by":"publisher","first-page":"888","DOI":"10.1080\/0951192X.2021.1925966","volume":"34","author":"T Wang","year":"2021","unstructured":"Wang T, Li J, Deng Y, Wang C, Snoussi H, Tao F (2021) Digital twin for human-machine interaction with convolutional neural network. Int J Comput Integr Manuf 34:888\u2013897. https:\/\/doi.org\/10.1080\/0951192X.2021.1925966","journal-title":"Int J Comput Integr Manuf"},{"key":"6916_CR108","doi-asserted-by":"publisher","unstructured":"G\u00f6rmez A, Koyuncu E. Pruning early exit networks. https:\/\/doi.org\/10.48550\/arXiv.2207.03644","DOI":"10.48550\/arXiv.2207.03644"},{"key":"6916_CR109","doi-asserted-by":"crossref","unstructured":"Fang G, Ma X, Song M, Mi MB, Wang X (2023) Depgraph: Towards any structural pruning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 16091\u201316101","DOI":"10.1109\/CVPR52729.2023.01544"},{"key":"6916_CR110","doi-asserted-by":"crossref","unstructured":"Park W, Kim D, Lu Y, Cho M (2019) Relational knowledge distillation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3967\u20133976","DOI":"10.1109\/CVPR.2019.00409"},{"key":"6916_CR111","unstructured":"Shah H, Khare A, Shah N, Siddiqui K (2020) KD-Lib: A PyTorch library for knowledge distillation, pruning and quantization"},{"key":"6916_CR112","unstructured":"Ameen S, Siriwardana K, Theodoridis T (2023) Optimizing Deep Learning Models For Raspberry Pi"},{"key":"6916_CR113","doi-asserted-by":"crossref","unstructured":"Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: unified, real-time object detection","DOI":"10.1109\/CVPR.2016.91"},{"key":"6916_CR114","doi-asserted-by":"crossref","unstructured":"Islam MR, Subramaniam M, Huang P-C (2024) Image-based deep learning for smart digital twins: a review","DOI":"10.1007\/s10462-024-11002-y"},{"key":"6916_CR115","unstructured":"Oktay D, Ball\u00e9 J, Singh S, Shrivastava A (2020) Scalable model compression by entropy penalized reparameterization. https:\/\/arxiv.org\/abs\/1906.06624"},{"key":"6916_CR116","doi-asserted-by":"crossref","unstructured":"Han L, Xiao Z, Li Z (2024) DTMM: Deploying TinyML models on extremely weak IoT devices with pruning. https:\/\/arxiv.org\/abs\/2401.09068","DOI":"10.1109\/INFOCOM52122.2024.10621387"},{"key":"6916_CR117","doi-asserted-by":"publisher","unstructured":"Shinde PP, Shah S (2018) A review of machine learning and deep learning applications. In: 2018 Fourth International Conference on Computing Communication Control and Automation (ICCUBEA), pp 1\u20136. https:\/\/doi.org\/10.1109\/ICCUBEA.2018.8697857","DOI":"10.1109\/ICCUBEA.2018.8697857"},{"key":"6916_CR118","doi-asserted-by":"publisher","unstructured":"Hassan F, Kumar V, Nishad AK, Gautam V (2023) Investigation of digital twin technology for secure and privacy preserving networking. Procedia Comput Sci 230:398\u2013406 . https:\/\/doi.org\/10.1016\/j.procs.2023.12.095. 3rd International Conference on Evolutionary Computing and Mobile Sustainable Networks (ICECMSN 2023)","DOI":"10.1016\/j.procs.2023.12.095"},{"key":"6916_CR119","doi-asserted-by":"publisher","first-page":"100230","DOI":"10.1016\/j.dajour.2023.100230","volume":"7","author":"A Saranya","year":"2023","unstructured":"Saranya A, Subhashini R (2023) A systematic review of explainable artificial intelligence models and applications: recent developments and future trends. Decis Anal J 7:100230. https:\/\/doi.org\/10.1016\/j.dajour.2023.100230","journal-title":"Decis Anal J"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-025-06916-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-025-06916-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-025-06916-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T08:03:15Z","timestamp":1764144195000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-025-06916-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,20]]},"references-count":119,"journal-issue":{"issue":"16","published-print":{"date-parts":[[2025,11]]}},"alternative-id":["6916"],"URL":"https:\/\/doi.org\/10.1007\/s10489-025-06916-1","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"type":"print","value":"0924-669X"},{"type":"electronic","value":"1573-7497"}],"subject":[],"published":{"date-parts":[[2025,10,20]]},"assertion":[{"value":"29 May 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 September 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 October 2025","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 they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of Interest"}}],"article-number":"1038"}}