{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T07:01:35Z","timestamp":1764831695634,"version":"3.46.0"},"reference-count":36,"publisher":"Tech Science Press","issue":"2","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["CMC"],"published-print":{"date-parts":[[2025]]},"DOI":"10.32604\/cmc.2025.064758","type":"journal-article","created":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T09:00:15Z","timestamp":1758618015000},"page":"4155-4171","source":"Crossref","is-referenced-by-count":0,"title":["Heuristic Weight Initialization for Transfer Learning in Classification Problems"],"prefix":"10.32604","volume":"85","author":[{"given":"Musulmon","family":"Lolaev","sequence":"first","affiliation":[]},{"given":"Anand","family":"Paul","sequence":"additional","affiliation":[]},{"given":"Jeonghong","family":"Kim","sequence":"additional","affiliation":[]}],"member":"17807","published-online":{"date-parts":[[2025]]},"reference":[{"key":"ref1","doi-asserted-by":"crossref","first-page":"781","DOI":"10.1007\/978-981-15-5971-6_83","author":"Panigrahi","year":"2021","journal-title":"Intelligent and cloud computing"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"3619","DOI":"10.3390\/math10193619","article-title":"A survey on deep transfer learning and beyond","volume":"10","author":"Yu","year":"2022","journal-title":"Mathematics"},{"key":"ref3","series-title":"2024 7th International Conference on Information and Communications Technology (ICOIACT)","first-page":"30","article-title":"Transfer learning in natural language processing","author":"Joseph","year":"2024 Nov 20\u201321"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1109\/JPROC.2020.3004555","article-title":"A comprehensive survey on transfer learning","volume":"109","author":"Zhuang","year":"2021","journal-title":"Proc IEEE"},{"key":"ref5","unstructured":"Reid M, Yamada Y, Gu SS. Can Wikipedia help offline reinforcement learning? arXiv:2201.12122. 2022."},{"key":"ref6","doi-asserted-by":"crossref","first-page":"801","DOI":"10.1109\/TPAMI.2018.2814042","article-title":"Beyond sharing weights for deep domain adaptation","volume":"41","author":"Rozantsev","year":"2016","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref7","series-title":"5th International Conference on Learning Representations, ICLR 2017","article-title":"Categorical reparametrization with Gumble-Softmax","author":"Jang","year":"2017 Apr 24\u201326"},{"key":"ref8","first-page":"12311","volume":"33","author":"Potapczynski","year":"2020","journal-title":"Invertible Gaussian reparameterization: revisiting the gumbel-softmax"},{"key":"ref9","series-title":"2019 IEEE\/CVF International Conference on Computer Vision (ICCV); 2019 Oct 27\u2013Nov 2","first-page":"4917","article-title":"Rethinking ImageNet pre-training","author":"He"},{"key":"ref10","series-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR); 2020 Jun 13\u201319","first-page":"10684","article-title":"Self-training with noisy student improves ImageNet classification","author":"Xie"},{"key":"ref11","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, et al. An image is worth 16 \u00d7 16 Words: transformers for image recognition at scale. arXiv: 2010.11929. 2021."},{"key":"ref12","series-title":"The 13th Pacific Rim International Conference on Artificial Intelligence; 2014 Dec 1\u20135","first-page":"898","article-title":"Domain adaptive neural networks for object recognition","author":"Ghifary"},{"key":"ref13","first-page":"1097","author":"Krizhevsky","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref14","series-title":"Proceedings of the 27th International Conference on Neural Information Processing Systems-Volume 2, NIPS\u201914","first-page":"3320","article-title":"How transferable are features in deep neural networks?","author":"Yosinski","year":"2014"},{"key":"ref15","series-title":"Computer Vision\u2013ECCV 2016 Workshops (ECCV 2016)","first-page":"435","article-title":"Best practices for fine-tuning visual classifiers to new domains","author":"Chu","year":"2016"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"1068","DOI":"10.1134\/S0005117911050146","article-title":"Computing generalized parameters and data mining","volume":"72","author":"Nikolay","year":"2011","journal-title":"Autom Remote Control"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"138","DOI":"10.3390\/technologies11050138","article-title":"Heuristic weight initialization for diagnosing heart diseases using feature ranking","volume":"11","author":"Musulmon","year":"2023","journal-title":"Technologies"},{"article-title":"Fixup initialization: residual learning without normalization","series-title":"7th International Conference on Learning Representations, ICLR 2019; 2019 May 6\u20139","author":"Zhang","key":"ref18"},{"key":"ref19","series-title":"Proceedings of the 2015 International Conference on Computer Vision (ICCV); 2015 Dec 7\u201313","first-page":"1316","article-title":"All you need is a good init","author":"Mishkin"},{"key":"ref20","series-title":"Proceedings of the Advances in Neural Information Processing Systems (NeurIPS); 2019 Dec 8\u201314","first-page":"3159","article-title":"MetaInit: initializing learning by learning to initialize","author":"Dauphin"},{"key":"ref21","series-title":"2021 IEEE\/CVF International Conference on Computer Vision (ICCV). 2021 Oct 10\u201317","first-page":"8320","article-title":"The many faces of robustness: a critical analysis of out-of-distribution generalization","author":"Hendrycks"},{"key":"ref22","series-title":"2017 IEEE International Conference on Computer Vision (ICCV). 2017 Oct 22\u201329","first-page":"843","article-title":"Revisiting unreasonable effectiveness of data in deep learning era","author":"Sun"},{"key":"ref23","series-title":"Proceedings of the 13th International Conference on Artificial Intelligence and Statistics (AISTATS) 2010; 2010 May 13\u201315","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"Glorot"},{"key":"ref24","series-title":"2015 IEEE International Conference on Computer Vision (ICCV). 2015 Dec 7\u201313","first-page":"1026","article-title":"Delving deep into rectifiers: surpassing human-level performance on ImageNet classification","author":"He"},{"key":"ref25","doi-asserted-by":"crossref","DOI":"10.1007\/978-0-387-84858-7","author":"Hastie","year":"2009","journal-title":"The elements of statistical learning: data mining, inference, and prediction"},{"key":"ref26","first-page":"239","author":"Negi","year":"2020","journal-title":"Gini index and entropy-based evaluation: a retrospective study and proposal of evaluation method for image segmentation"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1007\/978-3-642-76153-9_28","author":"Bridle","year":"1990","journal-title":"Neurocomputing"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1109\/72.991427","article-title":"A comparison of methods for multiclass support vector machines","volume":"13","author":"Hsu","year":"2002","journal-title":"IEEE Trans Neural Netw"},{"key":"ref29","unstructured":"Ma S, Wang H, Ma L, Wang L, Wang W, Huang S, et al. The era of 1-bit LLMs: all large language models are in 1.58 bits. arXiv:2402.17764. 2024."},{"journal-title":"Pattern recognition and machine learning (Information science and statistics)","year":"2007","author":"Bishop","key":"ref30"},{"journal-title":"Classification and regression trees","year":"1984","author":"Breiman","key":"ref31"},{"key":"ref32","first-page":"463","article-title":"Rademacher and Gaussian complexities: risk bounds and structural results","volume":"3","author":"Bartlett","year":"2002","journal-title":"J Mach Learn Res"},{"journal-title":"Statistical learning theory","year":"1998","author":"Vapnik","key":"ref33"},{"key":"ref34","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1023\/A:1022643204877","article-title":"Induction of decision trees","volume":"1","author":"Quinlan","year":"2004","journal-title":"Mach Learn"},{"key":"ref35","series-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies; 2019 Jun 2\u20137","first-page":"4171","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","author":"Devlin"},{"key":"ref36","series-title":"NIPS\u201921: Proceedings of the 35th International Conference on Neural Information Processing Systems; 2021 Dec 6\u201314","first-page":"24261","article-title":"MLP-Mixer: an all-MLP architecture for vision","author":"Tolstikhin"}],"container-title":["Computers, Materials & Continua"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/cdn.techscience.cn\/files\/cmc\/2025\/TSP_CMC-85-2\/TSP_CMC_64758\/TSP_CMC_64758.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T05:35:50Z","timestamp":1764826550000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.techscience.com\/cmc\/v85n2\/63783"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":36,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2025]]},"published-print":{"date-parts":[[2025]]}},"URL":"https:\/\/doi.org\/10.32604\/cmc.2025.064758","relation":{},"ISSN":["1546-2226"],"issn-type":[{"type":"electronic","value":"1546-2226"}],"subject":[],"published":{"date-parts":[[2025]]}}}