{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T22:35:28Z","timestamp":1765319728653,"version":"3.46.0"},"reference-count":56,"publisher":"Springer Science and Business Media LLC","issue":"36","license":[{"start":{"date-parts":[[2025,6,9]],"date-time":"2025-06-09T00:00:00Z","timestamp":1749427200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,6,9]],"date-time":"2025-06-09T00:00:00Z","timestamp":1749427200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100004895","name":"European Social Fund","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004895","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Image classification with deep neural networks has reached state-of-the-art with high accuracy. The unreasonable effectiveness of deep neural networks is credited to the manifold hypothesis that states natural data lies on a low-dimensional manifold embedded in the high-dimensional space. The machine learning models learn patterns on these low-rank representations, which gives the learning algorithms robustness. We test the robustness of learning algorithms using the paradigm of \u201cperturb and learn\u201d. This paper proposes a novel technique called Low-Rank Perturbation Adjustment (LoPA), an implicit regularization method used by machine learning models for resisting external perturbations. LoPA exploits the dependencies in model weights that lie in high-dimensional space and projects to low-dimensional while resisting perturbation. We validate LoPA through singular value decomposition (SVD) theory and empirical experiments, showing the statistical distribution of trained model weights of zero mean and small variance. We inject perturbations into our model by hot-swapping the activation functions and interchanging loss functions during the training. An InceptionV3 Neural Network is trained on common FruitFly Drosophila images for binary classification tasks of cancer cells. The Drosophila cancer images are prepared in our lab through immunostaining protocol.<\/jats:p>","DOI":"10.1007\/s11042-025-20941-9","type":"journal-article","created":{"date-parts":[[2025,6,9]],"date-time":"2025-06-09T07:26:01Z","timestamp":1749453961000},"page":"45581-45600","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Low-rank perturbation adjustment (LoPA): An implicit regularization method in image classification"],"prefix":"10.1007","volume":"84","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5618-2953","authenticated-orcid":false,"given":"Nesma Talaat Abbas","family":"Mahmoud","sequence":"first","affiliation":[]},{"given":"Hanna","family":"Antson","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3779-139X","authenticated-orcid":false,"given":"Wai Tik","family":"Chan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7322-078X","authenticated-orcid":false,"given":"Modar","family":"Sulaiman","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4663-3263","authenticated-orcid":false,"given":"Jaesik","family":"Choi","sequence":"additional","affiliation":[]},{"given":"Osamu","family":"Shimmi","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6557-2689","authenticated-orcid":false,"given":"Kallol","family":"Roy","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,6,9]]},"reference":[{"key":"20941_CR1","doi-asserted-by":"publisher","unstructured":"Su W, Zhu X, Tao C, Lu L, Li B, Huang G, Qiao Y, Wang X, Zhou J, Dai J (2023) Towards all-in-one pre-training via maximizing multi-modal mutual information. In: 2023 IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 15888\u201315899. https:\/\/doi.org\/10.1109\/CVPR52729.2023.01525","DOI":"10.1109\/CVPR52729.2023.01525"},{"key":"20941_CR2","unstructured":"Shinya Y (2022) USB: Universal-scale object detection benchmark. In: 33rd British machine vision conference 2022, (BMVC) 2022, London, UK, November 21\u201324, 2022. https:\/\/bmvc2022.mpi-inf.mpg.de\/0261.pdf"},{"key":"20941_CR3","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly S, Uszkoreit J, Houlsby N (2021) An image is worth 16x16 words: transformers for image recognition at scale. https:\/\/arxiv.org\/abs\/2010.11929"},{"key":"20941_CR4","unstructured":"Brown TB, Mann B, Ryder N, Subbiah M, Kaplan J, Dhariwal P, Neelakantan A, Shyam P, Sastry G, Askell A, Agarwal S, Herbert-Voss A, Krueger G, Henighan T, Child R, Ramesh A, Ziegler DM, Wu J, Winter C, Hesse C, Chen M, Sigler E, Litwin M, Gray S, Chess B, Clark J, Berner C, McCandlish S, Radford A, Sutskever I, Amodei D (2020) Language models are few-shot learners. In: Larochelle H, Ranzato M, Hadsell R, Balcan MF, Lin H (eds) Advances in neural information processing systems, vol 33. Curran Associates Inc., pp 1877\u20131901. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2020\/file\/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf"},{"key":"20941_CR5","unstructured":"Chowdhery A, Narang S, Devlin J, Bosma M, Mishra G, Roberts A, Barham P, Chung HW, Sutton C, Gehrmann S, Schuh P, Shi K, Tsvyashchenko S, Maynez J, Rao A, Barnes P, Tay Y, Shazeer N, Prabhakaran V, Reif E, Du N, Hutchinson B, Pope R, Bradbury J, Austin J, Isard M, Gur-Ari G, Yin P, Duke T, Levskaya A, Ghemawat S, Dev S, Michalewski H, Garcia X, Misra V, Robinson K, Fedus L, Zhou D, Ippolito D, Luan D, Lim H, Zoph B, Spiridonov A, Sepassi R, Dohan D, Agrawal S, Omernick M, Dai AM, Pillai TS, Pellat M, Lewkowycz A, Moreira E, Child R, Polozov O, Lee K, Zhou Z, Wang X, Saeta B, Diaz M, Firat O, Catasta M, Wei J, Meier-Hellstern K, Eck D, Dean J, Petrov S, Fiedel N (2023) PaLM: scaling language modeling with pathways. J Mach Learn Res 24(1):113"},{"key":"20941_CR6","unstructured":"Borgeaud S, Mensch A, Hoffmann J, Cai T, Rutherford E, Millican K, Van Den Driessche GB, Lespiau J-B, Damoc B, Clark A, de Las Casas D, Guy A, Menick J, Ring R, Hennigan T, Huang S, Maggiore L, Jones C, Cassirer A, Brock A, Paganini M, Irving G, Vinyals O, Osindero S, Simonyan K, Rae JW, Elsen E, Sifre L (2022) Improving language models by retrieving from trillions of tokens. In: International conference on machine learning, (ICML) 2022, 17\u201323 July 2022, Baltimore, Maryland, (USA), vol 162. PMLR, pp 2206\u20132240. https:\/\/proceedings.mlr.press\/v162\/borgeaud22a.html"},{"key":"20941_CR7","doi-asserted-by":"publisher","unstructured":"Schierholz M, Yang C, Roy K, Swaminathan M, Schuster C (2020) Comparison of collaborative versus extended artificial neural networks for pdn design. In: 2020 IEEE 24th workshop on signal and power integrity (SPI), pp 1\u20134. https:\/\/doi.org\/10.1109\/SPI48784.2020.9218157","DOI":"10.1109\/SPI48784.2020.9218157"},{"key":"20941_CR8","doi-asserted-by":"publisher","unstructured":"Roy K, Mert HT, Swaminathan M (2018) Preliminary application of deep learning to design space exploration. In: 2018 IEEE Electrical design of advanced packaging and systems symposium (EDAPS), pp 1\u20133. https:\/\/doi.org\/10.1109\/EDAPS.2018.8680888","DOI":"10.1109\/EDAPS.2018.8680888"},{"issue":"3","key":"20941_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TMAG.2017.2762351","volume":"54","author":"R Patel","year":"2018","unstructured":"Patel R, Roy K, Choi J, Han KJ (2018) Generative design of electromagnetic structures through bayesian learning. IEEE Trans Magnet 54(3):1\u20134. https:\/\/doi.org\/10.1109\/TMAG.2017.2762351","journal-title":"IEEE Trans Magnet"},{"key":"20941_CR10","doi-asserted-by":"publisher","unstructured":"Ostendorff M, Rethmeier N, Augenstein I, Gipp B, Rehm G (2022) Neighborhood contrastive learning for scientific document representations with citation embeddings. In: Goldberg Y, Kozareva Z, Zhang Y, (eds.) Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pp 11670\u201311688. Association for Computational Linguistics, Abu Dhabi, United Arab Emirates. https:\/\/doi.org\/10.18653\/v1\/2022.emnlp-main.802. https:\/\/aclanthology.org\/2022.emnlp-main.802\/","DOI":"10.18653\/v1\/2022.emnlp-main.802"},{"key":"20941_CR11","unstructured":"Goodfellow I, Bengio, Y, Courville A (2016) Deep learning. MIT press"},{"issue":"11","key":"20941_CR12","first-page":"7","volume":"2","author":"C Olah","year":"2017","unstructured":"Olah C, Mordvintsev A, Schubert L (2017) Feature visualization. Distill 2(11):7","journal-title":"Feature visualization. Distill"},{"key":"20941_CR13","doi-asserted-by":"crossref","unstructured":"Rumelhart DE, McClelland JL (1986) Learning internal representations by error propagation. In: Parallel distributed processing: explorations in the microstructure of cognition. pp 318\u2013362","DOI":"10.7551\/mitpress\/5236.001.0001"},{"issue":"3","key":"20941_CR14","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/BF02288367","volume":"1","author":"C Eckart","year":"1936","unstructured":"Eckart C, Young G (1936) The approximation of one matrix by another of lower rank. Psychometrika 1(3):211\u2013218. https:\/\/doi.org\/10.1007\/BF02288367","journal-title":"Psychometrika"},{"issue":"1","key":"20941_CR15","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1002\/gamm.201310004","volume":"36","author":"L Grasedyck","year":"2013","unstructured":"Grasedyck L, Kressner D, Tobler C (2013) A literature survey of low-rank tensor approximation techniques. GAMM-Mitteilungen 36(1):53\u201378","journal-title":"GAMM-Mitteilungen"},{"key":"20941_CR16","doi-asserted-by":"publisher","unstructured":"Elhamifar E, Vidal R (2011) Robust classification using structured sparse representation. In: CVPR 2011. IEEE, pp 1873\u20131879. https:\/\/doi.org\/10.1109\/CVPR.2011.5995664","DOI":"10.1109\/CVPR.2011.5995664"},{"key":"20941_CR17","doi-asserted-by":"crossref","unstructured":"Rodriguez F, Sapiro G (2008) Sparse representations for image classification: learning discriminative and reconstructive non-parametric dictionaries. University of Minnesota. Institute for Mathematics and Its Applications. https:\/\/conservancy.umn.edu\/items\/88bce62a-f706-414f-b083-4ffe3572a311","DOI":"10.21236\/ADA513220"},{"key":"20941_CR18","doi-asserted-by":"publisher","unstructured":"Yang J, Yu K, Gong Y (2009) Linear spatial pyramid matching using sparse coding for image classification. In: 2009 IEEE computer society conference on computer vision and pattern recognition workshops, CVPR workshops 2009. IEEE, pp 1794\u20131801. https:\/\/doi.org\/10.1109\/CVPR.2009.5206757","DOI":"10.1109\/CVPR.2009.5206757"},{"issue":"5","key":"20941_CR19","doi-asserted-by":"publisher","first-page":"1025","DOI":"10.1109\/JSTSP.2011.2157892","volume":"5","author":"MG Jafari","year":"2011","unstructured":"Jafari MG, Plumbley MD (2011) Fast dictionary learning for sparse representations of speech signals. IEEE J Selected Topics Signal Process 5(5):1025\u20131031","journal-title":"IEEE J Selected Topics Signal Process"},{"issue":"3","key":"20941_CR20","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1093\/bioinformatics\/btm601","volume":"24","author":"R Pique-Regi","year":"2008","unstructured":"Pique-Regi R, Monso-Varona J, Ortega A, Seeger RC, Triche TJ, Asgharzadeh S (2008) Sparse representation and bayesian detection of genome copy number alterations from microarray data. Bioinformatics 24(3):309\u2013318","journal-title":"Bioinformatics"},{"key":"20941_CR21","unstructured":"Oymak S, Fabian Z, Li M, Soltanolkotabi M (2019) Generalization guarantees for neural networks via harnessing the low-rank structure of the Jacobian. ArXiv abs\/1906.05392. https:\/\/api.semanticscholar.org\/CorpusID:189762232"},{"key":"20941_CR22","unstructured":"Frankle J, Carbin M (1803) The lottery ticket hypothesis: finding sparse, trainable neural networks. In: 7th International conference on learning representations, (ICLR) 2019, New Orleans, LA, USA, May 6\u20139, 2019. OpenReview.net.\u00a0https:\/\/openreview.net\/forum?id=rJl-b3RcF7"},{"key":"20941_CR23","unstructured":"Li C, Farkhoor H, Liu R, Yosinski J (2018) Measuring the intrinsic dimension of objective landscapes. CoRR abs\/1804.08838. https:\/\/arxiv.org\/abs\/1804.08838"},{"issue":"4","key":"20941_CR24","doi-asserted-by":"publisher","first-page":"1956","DOI":"10.1137\/080738970","volume":"20","author":"J-F Cai","year":"2010","unstructured":"Cai J-F, Cand\u00e8s EJ, Shen Z (2010) A singular value thresholding algorithm for matrix completion. SIAM J Optim 20(4):1956\u20131982","journal-title":"SIAM J Optim"},{"key":"20941_CR25","doi-asserted-by":"publisher","unstructured":"Zhao Y, Li J, Gong Y (2016) Low-rank plus diagonal adaptation for deep neural networks. In: 2016 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE, pp 5005\u20135009. https:\/\/doi.org\/10.1109\/ICASSP.2016.7472630","DOI":"10.1109\/ICASSP.2016.7472630"},{"issue":"8","key":"20941_CR26","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1109\/MC.2009.263","volume":"42","author":"Y Koren","year":"2009","unstructured":"Koren Y, Bell R, Volinsky C (2009) Matrix factorization techniques for recommender systems. Computer 42(8):30\u201337. https:\/\/doi.org\/10.1109\/MC.2009.263","journal-title":"Computer"},{"key":"20941_CR27","unstructured":"Neyshabur B, Li Z, Bhojanapalli S, LeCun Y, Srebro N (2018) The role of over-parametrization in generalization of neural networks. In: 7th International conference on learning representations, ICLR 2019"},{"key":"20941_CR28","unstructured":"Arora S, Cohen N, Hu W, Luo Y (2019) Implicit regularization in deep matrix factorization. In: Proceedings of the 33rd international conference on neural information processing systems. Curran Associates Inc., Red Hook, NY, USA, p 12"},{"key":"20941_CR29","doi-asserted-by":"publisher","unstructured":"Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z (2016) Rethinking the inception architecture for computer vision. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR). pp 2818\u20132826. https:\/\/doi.org\/10.1109\/CVPR.2016.308","DOI":"10.1109\/CVPR.2016.308"},{"key":"20941_CR30","first-page":"14820","volume":"33","author":"B Ghorbani","year":"2020","unstructured":"Ghorbani B, Mei S, Misiakiewicz T, Montanari A (2020) When do neural networks outperform kernel methods? Adv Neural Inf Process Syst 33:14820\u201314830","journal-title":"Adv Neural Inf Process Syst"},{"key":"20941_CR31","unstructured":"Li Y, Liang Y (2018) Learning overparameterized neural networks via stochastic gradient descent on structured data. In: Bengio S, Wallach HM, Larochelle H, Grauman K, Cesa-Bianchi N, Garnett R (eds) Advances in neural information processing systems 31: annual conference on neural information processing systems 2018,\u00a0NeurIPS 2018. Curran Associates, Inc., pp 8168\u20138177. https:\/\/proceedings.neurips.cc\/paper\/2018\/hash\/54fe976ba170c19ebae453679b362263-Abstract.html"},{"key":"20941_CR32","unstructured":"Allen-Zhu Z, Li Y (2023) Backward feature correction: how deep learning performs deep learning. CoRR abs\/2001.04413. https:\/\/arxiv.org\/abs\/2001.04413"},{"key":"20941_CR33","unstructured":"Allen-Zhu Z, Li Y, Song Z (2019) A convergence theory for deep learning via over-parameterization. In: Chaudhuri K, Salakhutdinov R (eds) Proceedings of the 36th international conference on machine learning, vol 97. PMLR, pp 242\u2013252. https:\/\/proceedings.mlr.press\/v97\/allen-zhu19a.html"},{"key":"20941_CR34","unstructured":"Allen-Zhu Z, Li Y (2019) What can ResNet learn efficiently, going beyond kernels? In: Advances in neural information processing systems 32: annual conference on neural information processing systems 2019, NeurIPS 2019. pp 9045\u20139025. https:\/\/proceedings.neurips.cc\/paper\/2019\/hash\/5857d68cd9280bc98d079fa912fd6740-Abstract.html"},{"key":"20941_CR35","doi-asserted-by":"crossref","unstructured":"Jaderberg M, Vedaldi A, Zisserman A (2014) Speeding up convolutional neural networks with low rank expansions. In: British Machine Vision Conference, (BMVC) 2014. (BMVA) Press. https:\/\/bmvaarchive.org.uk\/bmvc\/2014\/papers\/paper073\/index.html","DOI":"10.5244\/C.28.88"},{"key":"20941_CR36","unstructured":"Tai C, Xiao T, Zhang Y, Wang X et al (2015) Convolutional neural networks with low-rank regularization. In: 4th International conference on learning representations, (ICLR) 2016. https:\/\/arxiv.org\/abs\/1511.06067"},{"key":"20941_CR37","doi-asserted-by":"publisher","unstructured":"Povey D, Cheng G, Wang Y, Li K, Xu H, Yarmohammadi M, Khudanpur S (2018) Semi-orthogonal low-rank matrix factorization for deep neural networks. In: Interspeech, pp 3743\u20133747. https:\/\/doi.org\/10.21437\/Interspeech.2018-1417","DOI":"10.21437\/Interspeech.2018-1417"},{"key":"20941_CR38","unstructured":"Khodak M, Tenenholtz N, Mackey L, Fusi N (2021) Initialization and regularization of factorized neural layers. https:\/\/arxiv.org\/abs\/2105.01029"},{"key":"20941_CR39","unstructured":"Denil M, Shakibi B, Dinh L, Ranzato M, De Freitas N (2013) Predicting parameters in deep learning. In: Burges CJ, Bottou L, Welling M, Ghahramani Z, Weinberger KQ (eds) Advances in neural information processing systems, vol 26. Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2013\/file\/7fec306d1e665bc9c748b5d2b99a6e97-Paper.pdf"},{"key":"20941_CR40","doi-asserted-by":"publisher","unstructured":"Sainath TN, Kingsbury B, Sindhwani V, Arisoy E, Ramabhadran B (2013) Low-rank matrix factorization for deep neural network training with high-dimensional output targets. In: 2013 IEEE international conference on acoustics, speech and signal processing. IEEE, pp 6655\u20136659. https:\/\/doi.org\/10.1109\/ICASSP.2013.6638949","DOI":"10.1109\/ICASSP.2013.6638949"},{"key":"20941_CR41","doi-asserted-by":"publisher","unstructured":"Zhang Y, Chuangsuwanich E, Glass J (2014) Extracting deep neural network bottleneck features using low-rank matrix factorization. In: 2014 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE, pp 185\u2013189. https:\/\/doi.org\/10.1109\/ICASSP.2014.6853583","DOI":"10.1109\/ICASSP.2014.6853583"},{"key":"20941_CR42","unstructured":"Han S, Mao H, Dally WJ (2015) Deep compression: compressing deep neural networks with pruning, trained quantization and huffman coding. In: 4th International Conference on Learning Representations, (ICLR) 2016, San Juan, Puerto Rico, May 2-4, 2016, conference track proceedings. https:\/\/arxiv.org\/abs\/1510.00149"},{"key":"20941_CR43","unstructured":"Ioannou Y, Robertson DP, Shotton J, Cipolla R, Criminisi A (2015) Training cnns with low-rank filters for efficient image classification. CoRR abs\/1511.06744. https:\/\/api.semanticscholar.org\/CorpusID:11130812"},{"key":"20941_CR44","doi-asserted-by":"crossref","unstructured":"Lin Y, Sakr C, Kim Y, Shanbhag N (2017) Predictivenet: an energy-efficient convolutional neural network via zero prediction. In: 2017 IEEE International symposium on circuits and systems (ISCAS). IEEE, pp 1\u20134","DOI":"10.1109\/ISCAS.2017.8050797"},{"key":"20941_CR45","unstructured":"Denton E, Zaremba W, Bruna J, LeCun Y, Fergus R (2014) Exploiting linear structure within convolutional networks for efficient evaluation. In: Proceedings of the 28th international conference on neural information processing systems, vol 1. MIT Press, Cambridge, MA, USA, pp 1269\u20131277"},{"key":"20941_CR46","unstructured":"Elhage N, Hume T, Olsson C, Schiefer N, Henighan T, Kravec S, Hatfield-Dodds Z, Lasenby R, Drain D, Chen C, Grosse R, McCandlish S, Kaplan J, Amodei D, Wattenberg M, Olah C (2022) Toy models of superposition. https:\/\/arxiv.org\/abs\/2209.10652"},{"key":"20941_CR47","doi-asserted-by":"publisher","unstructured":"Liu B, Wang M, Foroosh H, Tappen M, Pensky M (2015) Sparse convolutional neural networks. In: 2015 IEEE conference on computer vision and pattern recognition (CVPR). IEEE, pp 806\u2013814. https:\/\/doi.org\/10.1109\/CVPR.2015.7298681","DOI":"10.1109\/CVPR.2015.7298681"},{"key":"20941_CR48","doi-asserted-by":"publisher","unstructured":"Allen-Zhu Z, Li Y (2022) Feature purification: how adversarial training performs robust deep learning. In: 2021 IEEE 62nd Annual symposium on foundations of computer science (FOCS), IEEE, pp 977\u2013988. https:\/\/doi.org\/10.1109\/FOCS52979.2021.00098","DOI":"10.1109\/FOCS52979.2021.00098"},{"key":"20941_CR49","unstructured":"Madry A, Makelov A, Schmidt L, Tsipras D,Vladu A (2017) Towards deep learning models resistant to adversarial attacks. https:\/\/arxiv.org\/abs\/1706.06083"},{"key":"20941_CR50","unstructured":"Tsuzuku Y, Sato I, Sugiyama M (2018) Lipschitz-margin training: scalable certification of perturbation invariance for deep neural networks. https:\/\/arxiv.org\/abs\/1802.04034"},{"issue":"3","key":"20941_CR51","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1145\/3446776","volume":"64","author":"C Zhang","year":"2021","unstructured":"Zhang C, Bengio S, Hardt M, Recht B, Vinyals O (2021) Understanding deep learning (still) requires rethinking generalization. Commun ACM 64(3):107\u2013115. https:\/\/doi.org\/10.1145\/3446776","journal-title":"Commun ACM"},{"key":"20941_CR52","unstructured":"Neyshabur B (2017) Implicit regularization in deep learning. https:\/\/arxiv.org\/abs\/1709.01953"},{"key":"20941_CR53","unstructured":"Arora S, Cohen N, Hu W, Luo Y (2019) Implicit regularization in deep matrix factorization. In: Wallach H, Larochelle H, Beygelzimer A et al (eds) Advances in neural information processing systems, vol 32. Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2019\/file\/c0c783b5fc0d7d808f1d14a6e9c8280d-Paper.pdf"},{"key":"20941_CR54","unstructured":"Neyshabur B, Tomioka R, Srebro N (2014) In search of the real inductive bias: on the role of implicit regularization in deep learning. In: Bengio Y, LeCun Y (eds) 3rd International conference on learning representations, (ICLR) 2015, San Diego, CA, USA, May 7\u20139, 2015, workshop track proceedings. https:\/\/arxiv.org\/abs\/1412.6614"},{"issue":"4","key":"20941_CR55","doi-asserted-by":"publisher","DOI":"10.1016\/j.xpro.2023.102566","volume":"4","author":"H Antson","year":"2023","unstructured":"Antson H, Huang Y, Tonissoo T, Shimmi O (2023) Conditional knockdown protocol for studying cellular communication using drosophila melanogaster wing imaginal disc. STAR Protocols 4(4):102566","journal-title":"STAR Protocols"},{"key":"20941_CR56","unstructured":"Hu EJ, Shen Y, Wallis P, Allen-Zhu Z, Li Y, Wang S, Wang L, Chen W (2021) LoRA: low-rank adaptation of large language models. https:\/\/arxiv.org\/abs\/2106.09685"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-025-20941-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-025-20941-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-025-20941-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T22:34:39Z","timestamp":1765319679000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-025-20941-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,9]]},"references-count":56,"journal-issue":{"issue":"36","published-online":{"date-parts":[[2025,11]]}},"alternative-id":["20941"],"URL":"https:\/\/doi.org\/10.1007\/s11042-025-20941-9","relation":{},"ISSN":["1573-7721"],"issn-type":[{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2025,6,9]]},"assertion":[{"value":"16 May 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 May 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 May 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 June 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not Applicable","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Approval"}},{"value":"All the Authors agree to publish the manuscript.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for Publication"}},{"value":"The authors have no financial or proprietary interests in any material discussed in this article.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of Interest"}}]}}