{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T14:49:20Z","timestamp":1773931760399,"version":"3.50.1"},"reference-count":302,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2019YFA0706200"],"award-info":[{"award-number":["2019YFA0706200"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62222603"],"award-info":[{"award-number":["62222603"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076102"],"award-info":[{"award-number":["62076102"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["92267203"],"award-info":[{"award-number":["92267203"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"STI2030-Major Projects Grant from the Ministry of Science and Technology of the Peoples Republic of China","award":["2021ZD0200700"],"award-info":[{"award-number":["2021ZD0200700"]}]},{"name":"Key-Area Research and Development Program of Guangdong Province","award":["2023B0303030001"],"award-info":[{"award-number":["2023B0303030001"]}]},{"name":"Guangdong Natural Science Funds for Distinguished Young Scholar","award":["2020B1515020041"],"award-info":[{"award-number":["2020B1515020041"]}]},{"name":"Program for Guangdong Introducing Innovative and Entrepreneurial Teams","award":["2019ZT08X214"],"award-info":[{"award-number":["2019ZT08X214"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1109\/tnnls.2024.3377194","type":"journal-article","created":{"date-parts":[[2024,4,9]],"date-time":"2024-04-09T19:38:36Z","timestamp":1712691516000},"page":"4246-4266","source":"Crossref","is-referenced-by-count":27,"title":["Dynamic Neural Network Structure: A Review for its Theories and Applications"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8520-3178","authenticated-orcid":false,"given":"Jifeng","family":"Guo","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5451-7230","authenticated-orcid":false,"given":"C. L. Philip","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4145-823X","authenticated-orcid":false,"given":"Zhulin","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0083-7656","authenticated-orcid":false,"given":"Xixin","family":"Yang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology and the School of Automation, Qingdao University, Qingdao, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3250490"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3262981"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2023.3253573"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2019.103378"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.105845"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2716952"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-022-01566-y"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2021.3110517"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2020.106698"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2020.3043147"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2022.3146983"},{"key":"ref12","first-page":"1453","article-title":"Online incremental feature learning with denoising autoencoders","volume-title":"Artificial Intelligence and Statistics","author":"Zhou","year":"2012"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1080\/09540098908915647"},{"issue":"3","key":"ref14","first-page":"175","article-title":"Adaptive dynamic RBF fuzzy neural controller design with a constructive learning","volume":"13","author":"Hsu","year":"2011","journal-title":"Int. J. Fuzzy Syst."},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2007.10.014"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM50108.2020.00118"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/1722024.1722044"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3151618"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3185527"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3082932"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3159661"},{"key":"ref22","article-title":"Progressive neural networks","author":"Rusu","year":"2016","journal-title":"arXiv:1606.04671"},{"key":"ref23","article-title":"Lifelong learning with dynamically expandable networks","author":"Yoon","year":"2017","journal-title":"arXiv:1708.01547"},{"key":"ref24","article-title":"Learned thresholds token merging and pruning for vision transformers","author":"Bonnaerens","year":"2023","journal-title":"arXiv:2307.10780"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01082"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.1991.155374"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/72.80236"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2017.01.033"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00983"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref31","first-page":"10183","article-title":"Synthesizer: Rethinking self-attention for transformer models","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Tay"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01185"},{"key":"ref33","first-page":"12934","article-title":"EfficientFormer: Vision transformers at MobileNet speed","volume-title":"Proc. Adv. Neural Inf. Process.","volume":"35","author":"Li"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/585"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071047"},{"key":"ref36","article-title":"Revisiting token pruning for object detection and instance segmentation","author":"Liu","year":"2023","journal-title":"arXiv:2306.07050"},{"key":"ref37","first-page":"13937","article-title":"DynamicViT: Efficient vision transformers with dynamic token sparsification","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Rao"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20202"},{"key":"ref39","article-title":"SPViT: Enabling faster vision transformers via soft token pruning","author":"Kong","year":"2021","journal-title":"arXiv:2112.13890"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_37"},{"key":"ref41","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654926"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.jobe.2021.103737"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.683"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.4324\/9781410605337-29"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2654543"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1611.01578"},{"key":"ref49","article-title":"Designing neural network architectures using reinforcement learning","author":"Baker","year":"2016","journal-title":"arXiv:1611.02167"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00907"},{"key":"ref51","article-title":"Hierarchical representations for efficient architecture search","author":"Liu","year":"2017","journal-title":"arXiv:1711.00436"},{"key":"ref52","article-title":"SMASH: One-shot model architecture search through HyperNetworks","author":"Brock","year":"2017","journal-title":"arXiv:1708.05344"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.109193"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2015.2494218"},{"key":"ref55","first-page":"7603","article-title":"Bayesnas: A Bayesian approach for neural architecture search","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhou"},{"key":"ref56","article-title":"Finding competitive network architectures within a day using UCT","author":"Wistuba","year":"2017","journal-title":"arXiv:1712.07420"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_11"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451394"},{"key":"ref59","article-title":"DARTS: Differentiable architecture search","author":"Liu","year":"2018","journal-title":"arXiv:1806.09055"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2022.3143201"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2023.3275128"},{"key":"ref62","article-title":"Efficient evaluation methods for neural architecture search: A survey","author":"Xie","year":"2023","journal-title":"arXiv:2301.05919"},{"key":"ref63","article-title":"Surrogate NAS benchmarks: Going beyond the limited search spaces of tabular NAS benchmarks","author":"Zela","year":"2020","journal-title":"arXiv:2008.09777"},{"key":"ref64","article-title":"Towards automated deep learning: Efficient joint neural architecture and hyperparameter search","author":"Zela","year":"2018","journal-title":"arXiv:1807.06906"},{"key":"ref65","first-page":"528","article-title":"Fast Bayesian optimization of machine learning hyperparameters on large datasets","volume-title":"Proc. 20th Int. Conf. Artif. Intell. Statist.","author":"Klein"},{"key":"ref66","article-title":"A downsampled variant of ImageNet as an alternative to the CIFAR datasets","author":"Chrabaszcz","year":"2017","journal-title":"arXiv:1707.08819"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014780"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2019.2924461"},{"key":"ref69","article-title":"Peephole: Predicting network performance before training","author":"Deng","year":"2017","journal-title":"arXiv:1712.03351"},{"key":"ref70","first-page":"550","article-title":"Understanding and simplifying one-shot architecture search","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bender"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_32"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01202"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/441"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00207"},{"key":"ref75","first-page":"594","article-title":"Overcoming multi-model forgetting","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Benyahia"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3035351"},{"key":"ref77","article-title":"DARTS+: Improved differentiable architecture search with early stopping","author":"Liang","year":"2019","journal-title":"arXiv:1909.06035"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1207\/s15516709cog1402_1"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TPEL.2010.2085454"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2014.01.015"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.4249\/scholarpedia.1977"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/s11071-022-07544-x"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1080\/00207160.2021.1939870"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3240403"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.5772\/10177"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1021\/acs.iecr.2c03339"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1016\/0022-2496(86)90043-X"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/21.87054"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2022.06.036"},{"key":"ref90","first-page":"875","article-title":"Generalization by weight-elimination with application to forecasting","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"3","author":"Weigend"},{"key":"ref91","first-page":"598","article-title":"Optimal brain damage","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"2","author":"LeCun"},{"key":"ref92","first-page":"177","article-title":"Comparing biases for minimal network construction with back-propagation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"1","author":"Hanson"},{"key":"ref93","first-page":"107","article-title":"Skeletonization: A technique for trimming the fat from a network via relevance assessment","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"1","author":"Mozer"},{"key":"ref94","article-title":"A unified framework for soft threshold pruning","author":"Chen","year":"2023","journal-title":"arXiv:2302.13019"},{"key":"ref95","article-title":"Predicting parameters in deep learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"26","author":"Denil"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1993.298572"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1010512"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS54959.2023.00033"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1016\/j.mechmachtheory.2023.105292"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2023.110757"},{"key":"ref101","article-title":"Why is the state of neural network pruning so confusing? On the fairness, comparison setup, and trainability in network pruning","author":"Wang","year":"2023","journal-title":"arXiv:2301.05219"},{"key":"ref102","article-title":"Less is more: The influence of pruning on the explainability of CNNs","author":"Weber","year":"2023","journal-title":"arXiv:2302.08878"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3117837"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7900006"},{"key":"ref106","first-page":"527","article-title":"Adaptive neural networks for efficient inference","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Bolukbasi"},{"key":"ref107","first-page":"18330","article-title":"BERT loses patience: Fast and robust inference with early exit","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Zhou"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_22"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/CODESISSS.2015.7331375"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3196959"},{"key":"ref111","first-page":"11960","article-title":"Not all images are worth 16=16 words: Dynamic transformers for efficient image recognition","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Wang"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-017-1029-1"},{"key":"ref113","article-title":"Energy-efficient amortized inference with cascaded deep classifiers","author":"Guan","year":"2017","journal-title":"arXiv:1710.03368"},{"key":"ref114","article-title":"Multi-scale dense networks for resource efficient image classification","author":"Huang","year":"2017","journal-title":"arXiv:1703.09844"},{"key":"ref115","first-page":"2363","article-title":"Deciding how to decide: Dynamic routing in artificial neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"McGill"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2959322"},{"key":"ref117","article-title":"Adaptive computation time for recurrent neural networks","author":"Graves","year":"2016","journal-title":"arXiv:1603.08983"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.194"},{"key":"ref119","article-title":"IamNN: Iterative and adaptive mobile neural network for efficient image classification","author":"Leroux","year":"2018","journal-title":"arXiv:1804.10123"},{"key":"ref120","article-title":"Universal transformers","author":"Dehghani","year":"2018","journal-title":"arXiv:1807.03819"},{"key":"ref121","article-title":"Dynamic token-pass transformers for semantic segmentation","author":"Liu","year":"2023","journal-title":"arXiv:2308.01944"},{"key":"ref122","article-title":"Depth-adaptive transformer","author":"Elbayad","year":"2019","journal-title":"arXiv:1910.10073"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00078"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_25"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_1"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00529"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00919"},{"key":"ref128","article-title":"Estimating or propagating gradients through stochastic neurons for conditional computation","author":"Bengio","year":"2013","journal-title":"arXiv:1308.3432"},{"key":"ref129","article-title":"Low-rank approximations for conditional feedforward computation in deep neural networks","author":"Davis","year":"2013","journal-title":"arXiv:1312.4461"},{"key":"ref130","article-title":"Learning factored representations in a deep mixture of experts","author":"Eigen","year":"2013","journal-title":"arXiv:1312.4314"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220007"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00843"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00027"},{"key":"ref135","article-title":"Structured pruning for deep convolutional neural networks: A survey","author":"He","year":"2023","journal-title":"arXiv:2303.00566"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3199703"},{"key":"ref137","article-title":"Channel gating neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Hua"},{"key":"ref138","article-title":"Dynamic channel pruning: Feature boosting and suppression","author":"Gao","year":"2018","journal-title":"arXiv:1810.05331"},{"key":"ref139","article-title":"Batch-shaping for learning conditional channel gated networks","author":"Ehteshami Bejnordi","year":"2019","journal-title":"arXiv:1907.06627"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/416"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2979669"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1109\/TETC.2021.3056031"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58285-2_3"},{"key":"ref144","article-title":"SaiT: Sparse vision transformers through adaptive token pruning","author":"Li","year":"2022","journal-title":"arXiv:2210.05832"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_24"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01054"},{"key":"ref147","article-title":"Efficient transformers with dynamic token pooling","author":"Nawrot","year":"2022","journal-title":"arXiv:2211.09761"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.463"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599284"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00775"},{"key":"ref151","article-title":"AdaViT: Adaptive tokens for efficient vision transformer","author":"Yin","year":"2021","journal-title":"arXiv:2112.07658"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43415-0_5"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475467"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11630"},{"key":"ref155","article-title":"DiT: Efficient vision transformers with dynamic token routing","author":"Ma","year":"2023","journal-title":"arXiv:2308.03409"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.18"},{"key":"ref157","article-title":"Distilling a neural network into a soft decision tree","author":"Frosst","year":"2017","journal-title":"arXiv:1711.09784"},{"key":"ref158","first-page":"4138","article-title":"The tree ensemble layer: Differentiability meets conditional computation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hazimeh"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.314"},{"key":"ref160","article-title":"Decision forests, convolutional networks and the models in-between","author":"Ioannou","year":"2016","journal-title":"arXiv:1603.01250"},{"key":"ref161","first-page":"6166","article-title":"Adaptive neural trees","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tanno"},{"key":"ref162","article-title":"CondConv: Conditionally parameterized convolutions for efficient inference","volume":"32","author":"Yang","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01104"},{"key":"ref164","first-page":"5047","article-title":"Meta-neighborhoods","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Shan"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00953"},{"key":"ref167","article-title":"Deformable kernels: Adapting effective receptive fields for object deformation","author":"Gao","year":"2019","journal-title":"arXiv:1910.02940"},{"key":"ref168","article-title":"Dynamic filter networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Jia"},{"key":"ref169","article-title":"HyperNetworks","author":"Ha","year":"2016","journal-title":"arXiv:1609.09106"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_46"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3253080"},{"key":"ref172","article-title":"LambdaNetworks: Modeling long-range interactions without attention","author":"Bello","year":"2021","journal-title":"arXiv:2102.08602"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.11"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3201198"},{"key":"ref176","article-title":"Incorporating side information by adaptive convolution","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Kang"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00907"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1109\/ICME46284.2020.9102906"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00928-1_48"},{"key":"ref180","article-title":"Gather-excite: Exploiting feature context in convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Hu"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3007884"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_21"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00060"},{"key":"ref184","article-title":"AutoScaler: Scale-attention networks for visual correspondence","author":"Wang","year":"2016","journal-title":"arXiv:1611.05837"},{"key":"ref185","article-title":"ConvBLS: An effective and efficient incremental convolutional broad learning system for image classification","author":"Lei","year":"2023","journal-title":"arXiv:2304.00219"},{"key":"ref186","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-020-09929-z"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.108730"},{"key":"ref188","first-page":"497","article-title":"Broad learning inference based on fully homomorphic encryption","volume-title":"Proc. Int. Conf. Parallel Distrib. Comput., Appl. Technol.","author":"Deng"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3181449"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3043110"},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3052102"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2021.103476"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.117390"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2025.107516"},{"key":"ref195","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2023.3305498"},{"issue":"6","key":"ref196","first-page":"1474","article-title":"An incremental disease prediction model based on denoising autoencoder with broad learning system","volume":"51","author":"Qi","year":"2023","journal-title":"Acta Electonica Sinica"},{"key":"ref197","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9533681"},{"key":"ref198","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108879"},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/3672905"},{"key":"ref200","doi-asserted-by":"publisher","DOI":"10.1109\/CAC51589.2020.9326897"},{"key":"ref201","article-title":"Efficient decremental learning algorithms for broad learning system","author":"Zhu","year":"2019","journal-title":"arXiv:1912.13169"},{"key":"ref202","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3137792"},{"key":"ref203","doi-asserted-by":"publisher","DOI":"10.1109\/tcds.2022.3192536"},{"key":"ref204","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2021.3112222"},{"key":"ref205","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3061428"},{"key":"ref206","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2023.3277102"},{"key":"ref207","doi-asserted-by":"publisher","DOI":"10.1007\/s00500-022-07718-0"},{"key":"ref208","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.119103"},{"key":"ref209","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3067028"},{"key":"ref210","doi-asserted-by":"publisher","DOI":"10.1109\/ICCSS.2016.7586428"},{"key":"ref211","doi-asserted-by":"publisher","DOI":"10.1109\/taffc.2023.3288885"},{"key":"ref212","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2020.2995205"},{"key":"ref213","article-title":"Reducing the computational complexity of pseudoinverse for the incremental broad learning system on added inputs","author":"Zhu","year":"2019","journal-title":"arXiv:1910.07755"},{"key":"ref214","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.3048990"},{"key":"ref215","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3171766"},{"key":"ref216","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00361"},{"key":"ref217","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3090260"},{"key":"ref218","article-title":"Two efficient ridge solutions for the incremental broad learning system on added inputs","author":"Zhu","year":"2019","journal-title":"arXiv:1911.07292"},{"key":"ref219","doi-asserted-by":"publisher","DOI":"10.1016\/j.ymssp.2022.109353"},{"key":"ref220","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-92537-0_27"},{"key":"ref221","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2019.2931255"},{"key":"ref222","doi-asserted-by":"publisher","DOI":"10.1109\/SPAC46244.2018.8965551"},{"key":"ref223","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3259016"},{"key":"ref224","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000013087.49260.fb"},{"key":"ref225","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299170"},{"key":"ref226","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.05.025"},{"key":"ref227","doi-asserted-by":"publisher","DOI":"10.5244\/C.29.32"},{"key":"ref228","doi-asserted-by":"publisher","DOI":"10.1109\/SmartWorld-UIC-ATC-ScalCom-DigitalTwin-PriComp-Metaverse56740.2022.00158"},{"key":"ref229","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.293"},{"key":"ref230","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.234"},{"key":"ref231","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2916104"},{"key":"ref232","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.684"},{"key":"ref233","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00858"},{"key":"ref234","doi-asserted-by":"publisher","DOI":"10.1016\/j.optlastec.2005.05.020"},{"key":"ref235","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00841"},{"key":"ref236","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_11"},{"key":"ref237","article-title":"Progressive neural networks for image classification","author":"Zhang","year":"2018","journal-title":"arXiv:1804.09803"},{"key":"ref238","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2019.2913999"},{"key":"ref239","doi-asserted-by":"publisher","DOI":"10.23919\/DATE56975.2023.10137239"},{"key":"ref240","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.67"},{"key":"ref241","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2017.2752806"},{"key":"ref242","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3146570"},{"key":"ref243","doi-asserted-by":"publisher","DOI":"10.1016\/j.chaos.2022.111889"},{"key":"ref244","doi-asserted-by":"publisher","DOI":"10.1088\/1674-1056\/ac3cb2"},{"key":"ref245","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2020.12.2754"},{"key":"ref246","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.593"},{"key":"ref247","article-title":"Neural speed reading with structural-jump-LSTM","author":"Hansen","year":"2019","journal-title":"arXiv:1904.00761"},{"key":"ref248","article-title":"Neural speed reading via skim-RNN","author":"Seo","year":"2017","journal-title":"arXiv:1711.02085"},{"key":"ref249","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p17-1172"},{"key":"ref250","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1474"},{"key":"ref251","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098177"},{"key":"ref252","first-page":"2554","article-title":"Focused hierarchical RNNs for conditional sequence processing","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ke"},{"key":"ref253","article-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","author":"Shazeer","year":"2017","journal-title":"arXiv:1701.06538"},{"key":"ref254","volume-title":"Fast and accurate text classification: Skimming, rereading and early stopping","author":"Yu","year":"2018"},{"key":"ref255","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.08.082"},{"key":"ref256","doi-asserted-by":"publisher","DOI":"10.1145\/3132847.3132947"},{"key":"ref257","article-title":"Variable computation in recurrent neural networks","author":"Jernite","year":"2016","journal-title":"arXiv:1611.06188"},{"key":"ref258","article-title":"Hierarchical multiscale recurrent neural networks","author":"Chung","year":"2016","journal-title":"arXiv:1609.01704"},{"key":"ref259","doi-asserted-by":"publisher","DOI":"10.1109\/NEBC.1995.513734"},{"key":"ref260","doi-asserted-by":"publisher","DOI":"10.1111\/exsy.12938"},{"key":"ref261","doi-asserted-by":"publisher","DOI":"10.1109\/ICFEICT59519.2023.00062"},{"key":"ref262","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1637"},{"key":"ref263","doi-asserted-by":"publisher","DOI":"10.1109\/tcds.2022.3147839"},{"key":"ref264","doi-asserted-by":"publisher","DOI":"10.1109\/tcss.2023.3298324"},{"key":"ref265","doi-asserted-by":"publisher","DOI":"10.1109\/CCECE.2012.6334837"},{"key":"ref266","doi-asserted-by":"publisher","DOI":"10.1115\/GT2010-23586"},{"key":"ref267","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2950240"},{"key":"ref268","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.120958"},{"key":"ref269","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2021.3085940"},{"key":"ref270","doi-asserted-by":"publisher","DOI":"10.1117\/12.150166"},{"key":"ref271","doi-asserted-by":"publisher","DOI":"10.1109\/ICSMC.1992.271599"},{"key":"ref272","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2007.907738"},{"key":"ref273","doi-asserted-by":"publisher","DOI":"10.3390\/e25070999"},{"key":"ref274","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2022.3188218"},{"key":"ref275","doi-asserted-by":"publisher","DOI":"10.1109\/ICSMC.2003.1245771"},{"key":"ref276","doi-asserted-by":"publisher","DOI":"10.1109\/ICSMC.1997.635144"},{"key":"ref277","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.119063"},{"key":"ref278","doi-asserted-by":"publisher","DOI":"10.5121\/ijaia.2017.8402"},{"key":"ref279","doi-asserted-by":"publisher","DOI":"10.1109\/NEMO49486.2020.9343530"},{"key":"ref280","doi-asserted-by":"publisher","DOI":"10.1109\/ICRIS.2018.00069"},{"key":"ref281","first-page":"1651","article-title":"Design of dynamic neural networks to forecast short-term railway passenger demand","volume":"6","author":"Tsai","year":"2005","journal-title":"J. Eastern Asia Soc. Transp. Stud."},{"key":"ref282","doi-asserted-by":"publisher","DOI":"10.1109\/INNOVATIONS.2006.301897"},{"key":"ref283","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-015-1991-z"},{"key":"ref284","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2021.103526"},{"key":"ref285","doi-asserted-by":"publisher","DOI":"10.1109\/34.204913"},{"key":"ref286","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3076683"},{"key":"ref287","doi-asserted-by":"publisher","DOI":"10.3390\/electronics11152322"},{"key":"ref288","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbad256"},{"key":"ref289","doi-asserted-by":"publisher","DOI":"10.3390\/fractalfract6070370"},{"key":"ref290","doi-asserted-by":"publisher","DOI":"10.3390\/app13042078"},{"key":"ref291","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2014.6889827"},{"key":"ref292","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3109276"},{"key":"ref293","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3201977"},{"key":"ref294","doi-asserted-by":"publisher","DOI":"10.1109\/ICCT46805.2019.8947271"},{"key":"ref295","doi-asserted-by":"publisher","DOI":"10.1049\/iet-gtd.2019.1371"},{"key":"ref296","doi-asserted-by":"publisher","DOI":"10.1016\/j.psep.2021.12.034"},{"key":"ref297","doi-asserted-by":"publisher","DOI":"10.1561\/2200000096"},{"key":"ref298","first-page":"107","article-title":"Dynamic feature space and incremental feature selection for the classification of textual data streams","author":"Katakis","year":"2006","journal-title":"Knowledge Discovery From Data Streams"},{"key":"ref299","first-page":"2432","article-title":"Glance and focus: A dynamic approach to reducing spatial redundancy in image classification","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Wang"},{"key":"ref300","doi-asserted-by":"publisher","DOI":"10.1145\/3431920.3439295"},{"key":"ref301","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2017.2682318"},{"key":"ref302","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1424-8"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10908444\/10492471.pdf?arnumber=10492471","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,3]],"date-time":"2025-03-03T18:36:47Z","timestamp":1741027007000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10492471\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":302,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2024.3377194","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3]]}}}