{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T16:09:55Z","timestamp":1786637395322,"version":"build-2736575974"},"reference-count":48,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2027,3,19]],"date-time":"2027-03-19T00:00:00Z","timestamp":1805414400000},"content-version":"am","delay-in-days":230,"URL":"http:\/\/www.elsevier.com\/open-access\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/100000006","name":"ONR","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.neunet.2026.108836","type":"journal-article","created":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T07:50:52Z","timestamp":1773301852000},"page":"108836","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Training sparse convolutional deep predictive coding networks with attention"],"prefix":"10.1016","volume":"200","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-7876-8825","authenticated-orcid":false,"given":"Hongming","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6150-2071","authenticated-orcid":false,"given":"Chi","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3449-3531","authenticated-orcid":false,"given":"Jos\u00e9 C","family":"Pr\u00edncipe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.108836_bib0001","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1137\/18M1183352","article-title":"Multi-layer sparse coding: The holistic way","volume":"1","author":"Aberdam","year":"2019","journal-title":"SIAM Journal on Mathematics of Data Science"},{"key":"10.1016\/j.neunet.2026.108836_bib0002","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1137\/080716542","article-title":"A fast iterative shrinkage-thresholding algorithm for linear inverse problems","volume":"2","author":"Beck","year":"2009","journal-title":"SIAM Journal on Imaging Sciences"},{"key":"10.1016\/j.neunet.2026.108836_bib0003","first-page":"153","article-title":"Greedy layer-wise training of deep networks","volume":"19","author":"Bengio","year":"2006","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.108836_bib0004","article-title":"Context dependent encoding using convolutional dynamic networks","volume":"26","author":"Chalasani","year":"1992","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.neunet.2026.108836_bib0005","unstructured":"Chalasani, R., & Principe, J. C. (2013). Deep predictive coding networks. arXiv preprint arXiv: 1301.3541."},{"key":"10.1016\/j.neunet.2026.108836_bib0006","doi-asserted-by":"crossref","first-page":"397","DOI":"10.2217\/nnm-2019-0436","article-title":"A surface-enhanced raman scattering-based probe method for detecting chromogranin a in adrenal tumors","volume":"15","author":"Cui","year":"2020","journal-title":"Nanomedicine : Nanotechnology, Biology, and Medicine"},{"key":"10.1016\/j.neunet.2026.108836_bib0007","doi-asserted-by":"crossref","first-page":"3333","DOI":"10.1109\/TPAMI.2020.2984244","article-title":"Deep convolutional neural network for multi-modal image restoration and fusion","volume":"43","author":"Deng","year":"2020","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2026.108836_bib0008","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1000211","article-title":"Hierarchical models in the brain","volume":"4","author":"Friston","year":"2008","journal-title":"PLoS Computational Biology"},{"key":"10.1016\/j.neunet.2026.108836_bib0009","doi-asserted-by":"crossref","first-page":"1211","DOI":"10.1098\/rstb.2008.0300","article-title":"Predictive coding under the free-energy principle","volume":"364","author":"Friston","year":"2009","journal-title":"Philosophical Transactions of the Royal Society B: Biological Sciences"},{"key":"10.1016\/j.neunet.2026.108836_bib0010","first-page":"429","article-title":"Theory of communication. part 1: The analysis of information","volume":"93","author":"Gabor","year":"1946","journal-title":"Journal of the Institution of Electrical Engineers-part III: Radio and Communication Engineering"},{"key":"10.1016\/j.neunet.2026.108836_bib0011","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1016\/0146-664X(78)90047-3","article-title":"In search of a general picture processing operator","volume":"8","author":"Granlund","year":"1978","journal-title":"Computer Graphics and Image Processing"},{"key":"10.1016\/j.neunet.2026.108836_bib0012","series-title":"Reducing the dimensionality of data with neural networks","first-page":"504","volume":"vol. 313","author":"Hinton","year":"2006"},{"key":"10.1016\/j.neunet.2026.108836_bib0013","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.108836_bib0014","series-title":"Proceedings of the 20th international conference on computer systems and technologies","first-page":"110","article-title":"Filters in convolutional neural networks as independent detectors of visual concepts","author":"Hristov","year":"2019"},{"key":"10.1016\/j.neunet.2026.108836_bib0015","doi-asserted-by":"crossref","first-page":"4448","DOI":"10.1109\/TFUZZ.2024.3399740","article-title":"High-order topology for deep single-cell multiview fuzzy clustering","volume":"32","author":"Hu","year":"2024","journal-title":"IEEE Transactions on Fuzzy Systems"},{"key":"10.1016\/j.neunet.2026.108836_bib0016","doi-asserted-by":"crossref","first-page":"483","DOI":"10.1093\/bib\/bbae483","article-title":"). SCEGG: An exogenous gene-guided clustering method for single-cell transcriptomic data","volume":"25","author":"Hu","year":"2024","journal-title":"Briefings in Bioinformatics"},{"key":"10.1016\/j.neunet.2026.108836_bib0017","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbae102","article-title":"Effective multi-modal clustering method via skip aggregation network for parallel SCRNA-SEQ and scatac-seq data","volume":"25","author":"Hu","year":"2024","journal-title":"Briefings in Bioinformatics"},{"key":"10.1016\/j.neunet.2026.108836_bib0018","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbad216","article-title":"SCDFC: A deep fusion clustering method for single-cell rna-seq data","volume":"24","author":"Hu","year":"2023","journal-title":"Briefings in Bioinformatics"},{"key":"10.1016\/j.neunet.2026.108836_bib0019","doi-asserted-by":"crossref","first-page":"125","DOI":"10.1016\/j.jphysparis.2006.09.011","article-title":"Learning receptive fields using predictive feedback","volume":"100","author":"Jehee","year":"2006","journal-title":"Journal of Physiology-Paris"},{"key":"10.1016\/j.neunet.2026.108836_bib0020","doi-asserted-by":"crossref","first-page":"8576","DOI":"10.1038\/s41598-024-59176-3","article-title":"Forward layer-wise learning of convolutional neural networks through separation index maximizing","volume":"14","author":"Karimi","year":"2024","journal-title":"Scientific Reports"},{"key":"10.1016\/j.neunet.2026.108836_bib0021","doi-asserted-by":"crossref","first-page":"397","DOI":"10.1162\/0899766053011474","article-title":"A hierarchical bayesian model for learning nonlinear statistical regularities in nonstationary natural signals","volume":"17","author":"Karklin","year":"2005","journal-title":"Neural Computation"},{"key":"10.1016\/j.neunet.2026.108836_bib0022","unstructured":"Kingma, D. P. (2013). Auto-encoding variational bayes. arXiv preprint arXiv: 1312.6114."},{"key":"10.1016\/j.neunet.2026.108836_bib0023","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"Krizhevsky","year":"2012","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.108836_bib0024","first-page":"3227","article-title":"Sparse coding for event-related potential detection from eeg","volume":"23","author":"Le","year":"2011","journal-title":"Neural Computation"},{"key":"10.1016\/j.neunet.2026.108836_bib0025","doi-asserted-by":"crossref","first-page":"274","DOI":"10.1016\/j.neunet.2022.02.029","article-title":"A self-learning cognitive architecture exploiting causality from rewards","volume":"150","author":"Li","year":"2022","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.108836_bib0026","unstructured":"Li, J., Feng, H., & Zhou, D.-X. (2024). Convergence analysis for deep sparse coding via convolutional neural networks. arXiv preprint arXiv: 2408.05540."},{"key":"10.1016\/j.neunet.2026.108836_bib0027","first-page":"10492","article-title":"Revisiting sparse convolutional model for visual recognition","volume":"35","author":"Li","year":"2022","journal-title":"Advances In Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.108836_bib0028","doi-asserted-by":"crossref","first-page":"607","DOI":"10.1038\/381607a0","article-title":"Emergence of simple-cell receptive field properties by learning a sparse code for natural images","volume":"381","author":"Olshausen","year":"1996","journal-title":"Nature"},{"key":"10.1016\/j.neunet.2026.108836_bib0029","doi-asserted-by":"crossref","first-page":"3311","DOI":"10.1016\/S0042-6989(97)00169-7","article-title":"Sparse coding with an overcomplete basis set: A strategy employed by v1?","volume":"37","author":"Olshausen","year":"1997","journal-title":"Vision Research"},{"key":"10.1016\/j.neunet.2026.108836_bib0030","first-page":"1","article-title":"Convolutional neural networks analyzed via convolutional sparse coding","volume":"18","author":"Papyan","year":"2017","journal-title":"Journal of Machine Learning Research"},{"key":"10.1016\/j.neunet.2026.108836_bib0031","doi-asserted-by":"crossref","first-page":"514","DOI":"10.1109\/JPROC.2014.2307023","article-title":"Cognitive architectures for sensory processing","volume":"102","author":"Principe","year":"2014","journal-title":"Proceedings of the IEEE"},{"key":"10.1016\/j.neunet.2026.108836_bib0032","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1038\/4580","article-title":"Predictive coding in the visual cortex: A functional interpretation of some extra-classical receptive-field effects","volume":"2","author":"Rao","year":"1999","journal-title":"Nature Neuroscience"},{"key":"10.1016\/j.neunet.2026.108836_bib0033","doi-asserted-by":"crossref","first-page":"1028","DOI":"10.1109\/TMI.2010.2090538","article-title":"Mr image reconstruction using sparsifying transforms","volume":"30","author":"Ravishankar","year":"2011","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"10.1016\/j.neunet.2026.108836_bib0034","doi-asserted-by":"crossref","first-page":"3738","DOI":"10.1109\/TNNLS.2017.2735903","article-title":"Exploiting spatio-temporal structure with recurrent winner-take-all networks","volume":"29","author":"Santana","year":"2017","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.neunet.2026.108836_bib0035","first-page":"2274","article-title":"Rethinking the csc model for natural images","volume":"32","author":"Simon","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.108836_bib0036","doi-asserted-by":"crossref","first-page":"5156","DOI":"10.1109\/TNNLS.2021.3115698","article-title":"Faster convergence in deep-predictive-coding networks to learn deeper representations","volume":"34","author":"Sledge","year":"2021","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.neunet.2026.108836_bib0037","first-page":"427","article-title":"Predictive coding: A fresh view of inhibition in the retina","volume":"216","author":"Srinivasan","year":"1982","journal-title":"Proceedings of the Royal Society of London. Series B. Biological Sciences"},{"key":"10.1016\/j.neunet.2026.108836_bib0038","first-page":"4090","article-title":"Multilayer convolutional sparse modeling: Pursuit and dictionary learning","volume":"66","author":"Sulam","year":"2018","journal-title":"IEEE Transactions on Signal Processing"},{"key":"10.1016\/j.neunet.2026.108836_bib0039","series-title":"2018 25th IEEE international conference on image processing","first-page":"346","article-title":"Supervised deep sparse coding networks","author":"Sun","year":"2018"},{"key":"10.1016\/j.neunet.2026.108836_bib0040","doi-asserted-by":"crossref","first-page":"405","DOI":"10.1109\/TIP.2019.2928121","article-title":"Supervised deep sparse coding networks for image classification","volume":"29","author":"Sun","year":"2019","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.neunet.2026.108836_bib0041","doi-asserted-by":"crossref","first-page":"7265","DOI":"10.1109\/JSEN.2020.2978772","article-title":"The layer-wise training convolutional neural networks using local loss for sensor-based human activity recognition","volume":"20","author":"Teng","year":"2020","journal-title":"IEEE Sensors Journal"},{"key":"10.1016\/j.neunet.2026.108836_bib0042","first-page":"3839","article-title":"Lipschitz regularity of deep neural networks: analysis and efficient estimation","volume":"31","author":"Virmaux","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.108836_bib0043","doi-asserted-by":"crossref","first-page":"1329","DOI":"10.1109\/TMI.2021.3054167","article-title":"Fista-net: Learning a fast iterative shrinkage thresholding network for inverse problems in imaging","volume":"40","author":"Xiang","year":"2021","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"10.1016\/j.neunet.2026.108836_bib0044","series-title":"2011 International conference on computer vision","first-page":"2018","article-title":"Adaptive deconvolutional networks for mid and high level feature learning","author":"Zeiler","year":"2011"},{"key":"10.1016\/j.neunet.2026.108836_bib0045","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1016\/j.patcog.2016.10.032","article-title":"Constructing deep sparse coding network for image classification","volume":"64","author":"Zhang","year":"2017","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.neunet.2026.108836_bib0046","series-title":"Proceedings of the ieee\/cvf conference on computer vision and pattern recognition","first-page":"2368","article-title":"Deep convolutional sparse coding networks for interpretable image fusion","author":"Zhao","year":"2023"},{"key":"10.1016\/j.neunet.2026.108836_bib0047","first-page":"1","article-title":"Scsc: Sparse coding for single-cell rna-seq clustering","volume":"19","author":"Zheng","year":"2018","journal-title":"Genome Biology"},{"key":"10.1016\/j.neunet.2026.108836_bib0048","series-title":"A stochastic grammar of images","first-page":"259","volume":"vol. 2","author":"Zhu","year":"2007"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026002984?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026002984?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T15:14:24Z","timestamp":1786634064000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026002984"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":48,"alternative-id":["S0893608026002984"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.108836","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Training sparse convolutional deep predictive coding networks with attention","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.108836","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"108836"}}