{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T19:59:19Z","timestamp":1781380759093,"version":"3.54.1"},"reference-count":44,"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":[[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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176040"],"award-info":[{"award-number":["62176040"]}],"id":[{"id":"10.13039\/501100001809","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.2026.108827","type":"journal-article","created":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T23:50:01Z","timestamp":1773273001000},"page":"108827","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["MD-LSM: an enabling tool for real-time monitoring linear separability of hidden-layer outputs of deep networks"],"prefix":"10.1016","volume":"200","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0142-0280","authenticated-orcid":false,"given":"Chao","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6754-5535","authenticated-orcid":false,"given":"Xinyu","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wensheng","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6868-5194","authenticated-orcid":false,"given":"Naizhe","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8304-3126","authenticated-orcid":false,"given":"Xingwu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.108827_bib0001","series-title":"Predictive Maintenance Dataset","year":"2020"},{"key":"10.1016\/j.neunet.2026.108827_bib0002","unstructured":"Alain, G., & Bengio, Y. (2016). Understanding intermediate layers using linear classifier probes. arXiv: 1610.01644."},{"key":"10.1016\/j.neunet.2026.108827_bib0003","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1016\/j.patrec.2023.11.016","article-title":"Hidden classification layers: Enhancing linear separability between classes in neural networks layers","volume":"177","author":"Apicella","year":"2024","journal-title":"Pattern Recognition Letters"},{"key":"10.1016\/j.neunet.2026.108827_bib0004","unstructured":"Arora, R., Basu, A., Mianjy, P., & Mukherjee, A. (2016). Understanding deep neural networks with rectified linear units. arXiv: 1611.01491."},{"key":"10.1016\/j.neunet.2026.108827_bib0005","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"16046","article-title":"Frozen feature augmentation for few-shot image classification","author":"B\u00e4r","year":"2024"},{"issue":"1","key":"10.1016\/j.neunet.2026.108827_bib0006","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1016\/j.laa.2005.08.014","article-title":"The geometry of linear separability in data sets","volume":"416","author":"Ben-Israel","year":"2006","journal-title":"Linear Algebra and its Applications"},{"key":"10.1016\/j.neunet.2026.108827_bib0007","series-title":"Topological, algebraic and geometric learning workshops 2022","first-page":"37","article-title":"Nearest class-center simplification through intermediate layers","author":"Ben-Shaul","year":"2022"},{"issue":"6","key":"10.1016\/j.neunet.2026.108827_bib0008","doi-asserted-by":"crossref","first-page":"1803","DOI":"10.1063\/1.1144830","article-title":"Neural networks and their applications","volume":"65","author":"Bishop","year":"1994","journal-title":"Review of Scientific Instruments"},{"key":"10.1016\/j.neunet.2026.108827_bib0009","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"3438","article-title":"Measuring and relieving the over-smoothing problem for graph neural networks from the topological view","volume":"vol. 34","author":"Chen","year":"2020"},{"key":"10.1016\/j.neunet.2026.108827_bib0010","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1023\/A:1022627411411","article-title":"Support-vector networks","volume":"20","author":"Cortes","year":"1995","journal-title":"Machine Learning"},{"issue":"3","key":"10.1016\/j.neunet.2026.108827_bib0011","doi-asserted-by":"crossref","first-page":"326","DOI":"10.1109\/PGEC.1965.264137","article-title":"Geometrical and statistical properties of systems of linear inequalities with applications in pattern recognition","volume":"EC-14","author":"Cover","year":"1965","journal-title":"IEEE Transactions on Electronic Computers"},{"key":"10.1016\/j.neunet.2026.108827_bib0012","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S. et al. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. arXiv: 2010.11929."},{"key":"10.1016\/j.neunet.2026.108827_bib0013","series-title":"IEEE international joint conference on neural networks","article-title":"Searching for linearly separable subsets using the class of linear separability method","author":"Elizondo","year":"2004"},{"issue":"3","key":"10.1016\/j.neunet.2026.108827_bib0014","doi-asserted-by":"crossref","first-page":"2330","DOI":"10.1016\/j.eswa.2010.08.021","article-title":"Choice effect of linear separability testing methods on constructive neural network algorithms: An empirical study","volume":"38","author":"Elizondo","year":"2010","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.neunet.2026.108827_bib0015","series-title":"Real-time collision detection","author":"Ericson","year":"2004"},{"issue":"2","key":"10.1016\/j.neunet.2026.108827_bib0016","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1111\/j.1469-1809.1936.tb02137.x","article-title":"The use of multiple measurements in taxonomic problems","volume":"7","author":"Fisher","year":"1936","journal-title":"Annals of Eugenics"},{"issue":"1","key":"10.1016\/j.neunet.2026.108827_bib0017","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1007\/s10957-012-0155-x","article-title":"A linear separability criterion for sets of euclidean space","volume":"158","author":"Gabidullina","year":"2013","journal-title":"Journal of Optimization Theory and Applications"},{"issue":"36","key":"10.1016\/j.neunet.2026.108827_bib0018","doi-asserted-by":"crossref","DOI":"10.1073\/pnas.2221704120","article-title":"A law of data separation in deep learning","volume":"120","author":"He","year":"2023","journal-title":"Proceedings of the National Academy of Sciences"},{"key":"10.1016\/j.neunet.2026.108827_bib0019","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"issue":"7","key":"10.1016\/j.neunet.2026.108827_bib0020","doi-asserted-by":"crossref","first-page":"1527","DOI":"10.1162\/neco.2006.18.7.1527","article-title":"A fast learning algorithm for deep belief nets","volume":"18","author":"Hinton","year":"2006","journal-title":"Neural Computation"},{"issue":"8","key":"10.1016\/j.neunet.2026.108827_bib0021","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural COMPUTATION"},{"issue":"5","key":"10.1016\/j.neunet.2026.108827_bib0022","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1016\/0893-6080(89)90020-8","article-title":"Multilayer feedforward networks are universal approximators","volume":"2","author":"Hornik","year":"1989","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.108827_bib0023","doi-asserted-by":"crossref","first-page":"2268","DOI":"10.52202\/068431-0165","article-title":"Not too little, not too much: A theoretical analysis of graph (over) smoothing","volume":"35","author":"Keriven","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.108827_bib0024","unstructured":"Keup, C., & Helias, M. (2022). Origami in n dimensions: How feed-forward networks manufacture linear separability. arXiv: 2203.11355."},{"key":"10.1016\/j.neunet.2026.108827_bib0025","unstructured":"Kipf, T. N., & Welling, M. (2016). Semi-supervised classification with graph convolutional networks. arXiv: 1609.02907."},{"key":"10.1016\/j.neunet.2026.108827_bib0026","series-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2012"},{"issue":"6","key":"10.1016\/j.neunet.2026.108827_bib0027","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1145\/3065386","article-title":"Imagenet classification with deep convolutional neural networks","volume":"60","author":"Krizhevsky","year":"2017","journal-title":"Communications of the ACM"},{"issue":"11","key":"10.1016\/j.neunet.2026.108827_bib0028","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"LeCun","year":"1998","journal-title":"Proceedings of the IEEE"},{"key":"10.1016\/j.neunet.2026.108827_bib0029","series-title":"2012\u202fIEEE 12th international conference on data mining","first-page":"499","article-title":"Efficient algorithms for finding richer subgroup descriptions in numeric and nominal data","author":"Mampaey","year":"2012"},{"key":"10.1016\/j.neunet.2026.108827_bib0030","unstructured":"Moro, S., Rita, P., & Cortez, P. (2014). Bank Marketing. UCI Machine Learning Repository. 10.24432\/C5K306."},{"key":"10.1016\/j.neunet.2026.108827_bib0031","unstructured":"Ng, A. Y., & Manning, C. D. (2024). Imdb movie review dataset. 10.57702\/d79z0npx."},{"issue":"1","key":"10.1016\/j.neunet.2026.108827_bib0032","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1109\/TVCG.2017.2744358","article-title":"Deepeyes: Progressive visual analytics for designing deep neural networks","volume":"24","author":"Pezzotti","year":"2017","journal-title":"IEEE Transactions on Visualization and Computer Graphics"},{"key":"10.1016\/j.neunet.2026.108827_bib0033","series-title":"International conference on machine learning","first-page":"28729","article-title":"Feature learning in deep classifiers through intermediate neural collapse","author":"Rangamani","year":"2023"},{"issue":"1","key":"10.1016\/j.neunet.2026.108827_bib0034","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1109\/TVCG.2016.2598838","article-title":"Visualizing the hidden activity of artificial neural networks","volume":"23","author":"Rauber","year":"2016","journal-title":"IEEE Transactions on Visualization and Computer Graphics"},{"key":"10.1016\/j.neunet.2026.108827_bib0035","doi-asserted-by":"crossref","first-page":"278","DOI":"10.1016\/j.neunet.2021.03.035","article-title":"Quantifying the separability of data classes in neural networks","volume":"139","author":"Schilling","year":"2021","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.108827_bib0036","unstructured":"Sigillito, V., Wing, S., Hutton, L., & Baker, K. (1989). Ionosphere. UCI Machine Learning Repository. 10.24432\/C5W01B."},{"key":"10.1016\/j.neunet.2026.108827_bib0037","unstructured":"Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv: 1409.1556."},{"key":"10.1016\/j.neunet.2026.108827_bib0038","doi-asserted-by":"crossref","first-page":"341","DOI":"10.1023\/A:1008202821328","article-title":"Differential evolution\u2013a simple and efficient heuristic for global optimization over continuous spaces","volume":"11","author":"Storn","year":"1997","journal-title":"Journal of Global Optimization"},{"key":"10.1016\/j.neunet.2026.108827_bib0039","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"1","article-title":"Going deeper with convolutions","author":"Szegedy","year":"2015"},{"issue":"1\u20134","key":"10.1016\/j.neunet.2026.108827_bib0040","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1016\/S0925-2312(01)00587-2","article-title":"New methods for testing linear separability","volume":"47","author":"Tajine","year":"2002","journal-title":"Neurocomputing"},{"issue":"3","key":"10.1016\/j.neunet.2026.108827_bib0041","doi-asserted-by":"crossref","first-page":"759","DOI":"10.1162\/NECO_a_00412","article-title":"A unified classification model based on robust optimization","volume":"25","author":"Takeda","year":"2013","journal-title":"Neural Computation"},{"issue":"4","key":"10.1016\/j.neunet.2026.108827_bib0042","doi-asserted-by":"crossref","DOI":"10.1137\/20M1314884","article-title":"Memory capacity of neural networks with threshold and rectified linear unit activations","volume":"2","author":"Vershynin","year":"2020","journal-title":"SIAM Journal on Mathematics of Data Science"},{"key":"10.1016\/j.neunet.2026.108827_bib0043","unstructured":"Wolberg, W., Mangasarian, O., Street, N., & Street, W. (1993). Breast Cancer Wisconsin (Diagnostic). UCI Machine Learning Repository. 10.24432\/C5DW2B."},{"key":"10.1016\/j.neunet.2026.108827_bib0044","series-title":"Proceedings of the 2020 conference on empirical methods in natural language processing: System demonstrations","first-page":"38","article-title":"Transformers: State-of-the-art natural language processing","author":"Wolf","year":"2020"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026002893?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026002893?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T06:46:19Z","timestamp":1779691579000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026002893"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":44,"alternative-id":["S0893608026002893"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.108827","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":"MD-LSM: an enabling tool for real-time monitoring linear separability of hidden-layer outputs of deep networks","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.108827","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":"108827"}}