{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T14:44:10Z","timestamp":1768401850781,"version":"3.49.0"},"reference-count":34,"publisher":"World Scientific Pub Co Pte Ltd","issue":"01","funder":[{"DOI":"10.13039\/501100004113","name":"University Libanaise","doi-asserted-by":"publisher","award":["428\/215"],"award-info":[{"award-number":["428\/215"]}],"id":[{"id":"10.13039\/501100004113","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Vietnam J. Comp. Sci."],"published-print":{"date-parts":[[2026,2]]},"abstract":"<jats:p>A Deep Spiking Neural Network (DSNN) with Heterogeneous Regularization learning technique is proposed to build a more biologically plausible approach that evaluates the amount of noise and finds a stopping criterion for fast realistic illumination. Our contribution is to introduce a model that improves the label propagation of DSNN and is more efficient on neuromorphic hardware than a corresponding Artificial Neural Network. More specifically, we develop a biological neural model with a heterogeneous regularization technique that works similarly to a human brain and can detect noise using deep spikes without relying on mathematical metrics to extract noise features. The objective function of the proposed DSNN consists of a supervised term and an unsupervised term. The supervised term enforces the matching term between the predicted labels and the known labels. The unsupervised term enforces the smoothness of the predicted labels of the entire data samples. By learning a DSNN with the proposed objective function, we are able to develop a more powerful learning algorithm. Experiments were conducted using scenes with Global Illumination and various image distortions. The proposed model was also compared with the human visual system and other state-of-the-art models. The results show better performance and advantages in terms of efficiency, an increasingly biologically plausible network, and ease of implementation in Neuromorphic Hardware.<\/jats:p>","DOI":"10.1142\/s2196888824400049","type":"journal-article","created":{"date-parts":[[2024,12,20]],"date-time":"2024-12-20T10:31:55Z","timestamp":1734690715000},"page":"1-28","source":"Crossref","is-referenced-by-count":0,"title":["Heterogeneous Regularization for Fast Rendering Using Deep Spike Neural Network"],"prefix":"10.1142","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7911-1218","authenticated-orcid":false,"given":"Joseph","family":"Constantin","sequence":"first","affiliation":[{"name":"LaRRIS, Faculty of Sciences, Lebanese University, Fanar, BP 90656, Jdeidet, Lebanon"},{"name":"Ho Chi Minh City Open University, Ho Chi Minh City, Vi\u00eat Nam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4252-0819","authenticated-orcid":false,"given":"Ibtissam","family":"Constantin","sequence":"additional","affiliation":[{"name":"LaRRIS, Faculty of Sciences, Lebanese University, Fanar, BP 90656, Jdeidet, Lebanon"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6581-9680","authenticated-orcid":false,"given":"Fadi","family":"Dornaika","sequence":"additional","affiliation":[{"name":"Ho Chi Minh City Open University, Ho Chi Minh City, Vi\u00eat Nam"},{"name":"University of the Basque Country UPV\/EHU, San Sebastian, Spain"},{"name":"IKERBASQUE, Basque Foundation for Science, Bilbao, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3464-3894","authenticated-orcid":false,"given":"Vinh Truong","family":"Hoang","sequence":"additional","affiliation":[{"name":"Ho Chi Minh City Open University, Ho Chi Minh City, Vi\u00eat Nam"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"219","published-online":{"date-parts":[[2025,2,14]]},"reference":[{"key":"S2196888824400049BIB001","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14342"},{"key":"S2196888824400049BIB002","doi-asserted-by":"publisher","DOI":"10.1145\/2366145.2366166"},{"key":"S2196888824400049BIB003","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2465960"},{"key":"S2196888824400049BIB004","doi-asserted-by":"publisher","DOI":"10.1145\/2614348.2614357"},{"key":"S2196888824400049BIB005","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2006.881959"},{"key":"S2196888824400049BIB006","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2014.10.090"},{"key":"S2196888824400049BIB007","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2008.02.003"},{"key":"S2196888824400049BIB008","doi-asserted-by":"publisher","DOI":"10.3390\/e23010075"},{"key":"S2196888824400049BIB009","doi-asserted-by":"publisher","DOI":"10.3390\/jimaging6090091"},{"key":"S2196888824400049BIB010","doi-asserted-by":"crossref","unstructured":"J. Eshraghian, M. Ward, E. Neftci, X. Wang, G. Lenz, G. Dwivedi, M. Bennamoun, D. Jeong and W. Lu Training spiking neural networks using lessons from deep learning, preprint (2023), arXiv:2109.12894.","DOI":"10.1109\/JPROC.2023.3308088"},{"key":"S2196888824400049BIB011","unstructured":"W. Zhang and P. Li, Temporal spike sequence learning via backpropagation for deep spiking neural networks, preprint (2021), arXiv:2002.10085."},{"key":"S2196888824400049BIB012","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2019.2931595"},{"key":"S2196888824400049BIB013","doi-asserted-by":"publisher","DOI":"10.1142\/S0129065720500276"},{"key":"S2196888824400049BIB014","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01357"},{"key":"S2196888824400049BIB015","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2020.00535"},{"key":"S2196888824400049BIB016","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2017.12.005"},{"key":"S2196888824400049BIB017","first-page":"49","volume":"69","author":"Constantin J.","year":"2019","journal-title":"Neural Comput. Appl."},{"key":"S2196888824400049BIB018","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14378"},{"key":"S2196888824400049BIB019","unstructured":"S. Hadadan and M. Zwicker, Differentiable neural radiosity, preprint (2022), arXiv:2201. 13190."},{"key":"S2196888824400049BIB020","doi-asserted-by":"publisher","DOI":"10.1145\/226150.226151"},{"key":"S2196888824400049BIB021","unstructured":"E. Hunsberger and C. Eliasmith, Training spiking deep networks for neuromorphic hardware, preprint (2016), arXiv:1611.05141."},{"key":"S2196888824400049BIB022","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2017.09.008"},{"key":"S2196888824400049BIB023","doi-asserted-by":"publisher","DOI":"10.1007\/s12021-019-09424-z"},{"key":"S2196888824400049BIB024","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2015.7280390"},{"key":"S2196888824400049BIB025","unstructured":"T. N. Kipf and M. Welling, Semi-supervised classification with graph convolutional networks, preprint (2016), arXiv:1609.02907."},{"key":"S2196888824400049BIB026","unstructured":"D. P. Kingma and J. Ba, Adam: A method for stochastic optimization, preprint (2017), arXiv:1412.6980."},{"key":"S2196888824400049BIB027","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511810114"},{"key":"S2196888824400049BIB028","doi-asserted-by":"publisher","DOI":"10.1007\/s00500-023-09309-z"},{"key":"S2196888824400049BIB029","first-page":"45","volume-title":"2nd European Workshop on Visual Information Processing (EUVIP)","author":"Lahoudou A.","year":"2010"},{"key":"S2196888824400049BIB030","first-page":"219","volume-title":"The 7th Int. Workshop on Systems, Signal Processing and Their Applications","author":"Lahoudou A.","year":"2011"},{"issue":"2","key":"S2196888824400049BIB031","first-page":"184","volume":"3","author":"Choi M.","year":"2009","journal-title":"Int. J. Electr. Comput. Eng."},{"key":"S2196888824400049BIB032","doi-asserted-by":"publisher","DOI":"10.1007\/s12652-021-03488-z"},{"key":"S2196888824400049BIB033","doi-asserted-by":"publisher","DOI":"10.1007\/s10055-023-00921-w"},{"key":"S2196888824400049BIB034","doi-asserted-by":"publisher","DOI":"10.1145\/3406183"}],"container-title":["Vietnam Journal of Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.worldscientific.com\/doi\/pdf\/10.1142\/S2196888824400049","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T09:04:02Z","timestamp":1768381442000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.worldscientific.com\/doi\/10.1142\/S2196888824400049"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,14]]},"references-count":34,"journal-issue":{"issue":"01","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["10.1142\/S2196888824400049"],"URL":"https:\/\/doi.org\/10.1142\/s2196888824400049","relation":{},"ISSN":["2196-8888","2196-8896"],"issn-type":[{"value":"2196-8888","type":"print"},{"value":"2196-8896","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,14]]}}}