{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,28]],"date-time":"2026-02-28T04:23:24Z","timestamp":1772252604116,"version":"3.50.1"},"reference-count":120,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2021,8,22]],"date-time":"2021-08-22T00:00:00Z","timestamp":1629590400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100014013","name":"UK Research and Innovation","doi-asserted-by":"publisher","award":["Alan Turing AI Acceleration Fellowship EP\/V025295\/1"],"award-info":[{"award-number":["Alan Turing AI Acceleration Fellowship EP\/V025295\/1"]}],"id":[{"id":"10.13039\/100014013","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012190","name":"Ministry of Science and Higher Education of the Russian Federation","doi-asserted-by":"publisher","award":["075-15-2020-808"],"award-info":[{"award-number":["075-15-2020-808"]}],"id":[{"id":"10.13039\/501100012190","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>This work is driven by a practical question: corrections of Artificial Intelligence (AI) errors. These corrections should be quick and non-iterative. To solve this problem without modification of a legacy AI system, we propose special \u2018external\u2019 devices, correctors. Elementary correctors consist of two parts, a classifier that separates the situations with high risk of error from the situations in which the legacy AI system works well and a new decision that should be recommended for situations with potential errors. Input signals for the correctors can be the inputs of the legacy AI system, its internal signals, and outputs. If the intrinsic dimensionality of data is high enough then the classifiers for correction of small number of errors can be very simple. According to the blessing of dimensionality effects, even simple and robust Fisher\u2019s discriminants can be used for one-shot learning of AI correctors. Stochastic separation theorems provide the mathematical basis for this one-short learning. However, as the number of correctors needed grows, the cluster structure of data becomes important and a new family of stochastic separation theorems is required. We refuse the classical hypothesis of the regularity of the data distribution and assume that the data can have a rich fine-grained structure with many clusters and corresponding peaks in the probability density. New stochastic separation theorems for data with fine-grained structure are formulated and proved. On the basis of these theorems, the multi-correctors for granular data are proposed. The advantages of the multi-corrector technology were demonstrated by examples of correcting errors and learning new classes of objects by a deep convolutional neural network on the CIFAR-10 dataset. The key problems of the non-classical high-dimensional data analysis are reviewed together with the basic preprocessing steps including the correlation transformation, supervised Principal Component Analysis (PCA), semi-supervised PCA, transfer component analysis, and new domain adaptation PCA.<\/jats:p>","DOI":"10.3390\/e23081090","type":"journal-article","created":{"date-parts":[[2021,8,22]],"date-time":"2021-08-22T21:47:52Z","timestamp":1629668872000},"page":"1090","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["High-Dimensional Separability for One- and Few-Shot Learning"],"prefix":"10.3390","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6224-1430","authenticated-orcid":false,"given":"Alexander N.","family":"Gorban","sequence":"first","affiliation":[{"name":"Department of Mathematics, University of Leicester, Leicester LE1 7RH, UK"},{"name":"Laboratory of Advanced Methods for High-Dimensional Data Analysis, Lobachevsky University, 603105 Nizhni Novgorod, Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2624-5765","authenticated-orcid":false,"given":"Bogdan","family":"Grechuk","sequence":"additional","affiliation":[{"name":"Department of Mathematics, University of Leicester, Leicester LE1 7RH, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1474-1734","authenticated-orcid":false,"given":"Evgeny M.","family":"Mirkes","sequence":"additional","affiliation":[{"name":"Department of Mathematics, University of Leicester, Leicester LE1 7RH, UK"},{"name":"Laboratory of Advanced Methods for High-Dimensional Data Analysis, Lobachevsky University, 603105 Nizhni Novgorod, Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3032-5469","authenticated-orcid":false,"given":"Sergey V.","family":"Stasenko","sequence":"additional","affiliation":[{"name":"Laboratory of Advanced Methods for High-Dimensional Data Analysis, Lobachevsky University, 603105 Nizhni Novgorod, Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7359-7966","authenticated-orcid":false,"given":"Ivan Y.","family":"Tyukin","sequence":"additional","affiliation":[{"name":"Department of Mathematics, University of Leicester, Leicester LE1 7RH, UK"},{"name":"Laboratory of Advanced Methods for High-Dimensional Data Analysis, Lobachevsky University, 603105 Nizhni Novgorod, Russia"},{"name":"Department of Geoscience and Petroleum, Norwegian University of Science and Technology, 7491 Trondheim, Norway"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2021,8,22]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1080\/0952813X.2014.895105","article-title":"The errors, insights and lessons of famous AI predictions and what they mean for the future","volume":"26","author":"Armstrong","year":"2014","journal-title":"J. Exp. Theor. Artif. Intell."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1007\/978-3-030-64731-5_5","article-title":"AI Turning points and the road ahead","volume":"Volume 893","author":"Sabourin","year":"2021","journal-title":"Computational Intelligence: Proceedings of the 10th International Joint Conference on Computational Intelligence (IJCCI 2018)"},{"key":"ref_3","unstructured":"John, W., and Lloyd, J.W. (1995). Surviving the AI winter. Logic Programming: The 1995 International Symposium, MIT Press."},{"key":"ref_4","first-page":"2","article-title":"Avoiding another AI winter","volume":"23","author":"Hendler","year":"2008","journal-title":"IEEE Intell. Syst."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s13347-020-00396-6","article-title":"AI and its new winter: From myths to realities","volume":"33","author":"Floridi","year":"2020","journal-title":"Philos. Technol."},{"key":"ref_6","unstructured":"Bowman, C.E., and Grindrod, P. (2021, August 12). Trust, Limitation, Conflation and Hype. ResearchGate Preprint. Available online: https:\/\/www.researchgate.net\/publication\/334425107_Trust_Limitation_Conflation_and_Hype."},{"key":"ref_7","unstructured":"(2021, August 12). Gartner Hype Cycle for Artificial Intelligence. Available online: https:\/\/www.gartner.com\/smarterwithgartner\/toptrends-on-the-gartner-hype-cycle-for-artificial-intelligence-2019\/."},{"key":"ref_8","unstructured":"(2021, August 12). Gartner Hype Cycle for Emerging Technologies. Available online: https:\/\/www.gartner.com\/en\/newsroom\/pressreleases\/2020-08-18-gartner-identifies-five-emerging-trends-that-will-drive-technology-innovation-for-the-next-decade."},{"key":"ref_9","unstructured":"Gorban, A.N., Grechuk, B., and Tyukin, I.Y. (2018). Augmented Artificial Intelligence: A Conceptual Framework. arXiv."},{"key":"ref_10","unstructured":"Yeung, K. (2021, August 12). Responsibility and AI: Council of Europe Study DGI(2019)05. Available online: https:\/\/rm.coe.int\/responsability-and-ai-en\/168097d9c5."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1090\/S0273-0979-01-00923-5","article-title":"On the mathematical foundations of learning","volume":"39","author":"Cucker","year":"2002","journal-title":"Bull. Am. Math. Soc."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Friedman, J., Hastie, T., and Tibshirani, R. (2009). The Elements of Statistical Learning, Springer.","DOI":"10.1007\/978-0-387-84858-7"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1016\/j.neunet.2021.01.034","article-title":"General stochastic separation theorems with optimal bounds","volume":"138","author":"Grechuk","year":"2021","journal-title":"Neural Netw."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Rosenblatt, F. (1962). Principles of Neurodynamics: Perceptrons and the Theory of Brain Mechanisms, Spartan Books.","DOI":"10.21236\/AD0256582"},{"key":"ref_15","unstructured":"Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning, MIT Press."},{"key":"ref_16","unstructured":"Talvitie, E. (2014, January 23\u201327). Model regularization for stable sample rollouts. Proceedings of the 30th Conference on Uncertainty in Artificial Intelligence, Lancaster, PA, USA."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Venkatraman, A., Hebert, M., and Bagnell, J.A. (2015, January 25\u201329). Improving multistep prediction of learned time series models. Proceedings of the 29th AAAI Conference on Artificial Intelligence, Austin, TX, USA.","DOI":"10.1609\/aaai.v29i1.9590"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Talvitie, E. (2017, January 4\u20139). Self-correcting models for model-based reinforcement learning. Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, San Francisco, CA, USA.","DOI":"10.1609\/aaai.v31i1.10850"},{"key":"ref_19","unstructured":"Vinyals, O., Blundell, C., Lillicrap, T., Kavukcuoglu, K., and Wierstra, D. (2016, January 5). Matching networks for one shot learning. Proceedings of the NIPS\u201916: 30th International Conference on Neural Information Processing Systems, Barcelona, Spain."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1145\/3446776","article-title":"Understanding deep learning (still) requires rethinking generalization","volume":"64","author":"Zhang","year":"2021","journal-title":"Commun. ACM"},{"key":"ref_21","unstructured":"Snell, J., Swersky, K., and Zemel, R. (2017, January 4). Prototypical networks for few-shot learning. Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, CA, USA. Available online: https:\/\/proceedings.neurips.cc\/paper\/2017\/file\/cb8da6767461f2812ae4290eac7cbc42-Paper.pdf."},{"key":"ref_22","unstructured":"Ravi, S., and Larochelle, H. (2017, January 24\u201326). Optimization as a model for few-shot learning. Proceedings of the International Conference on Learning Representations, Toulon, France. Available online: https:\/\/openreview.net\/pdf?id=rJY0-Kcll."},{"key":"ref_23","first-page":"1","article-title":"Generalizing from a few examples: A survey on few-shot learning","volume":"53","author":"Wang","year":"2020","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Sung, F., Yang, Y., Zhang, L., Xiang, T., Torr, P.H., and Hospedales, T.M. (2018, January 19\u201321). Learning to Compare: Relation Network for Few-Shot Learning. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA. Available online: https:\/\/openaccess.thecvf.com\/content_cvpr_2018\/html\/Sung_Learning_to_Compare_CVPR_2018_paper.html.","DOI":"10.1109\/CVPR.2018.00131"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"20170237","DOI":"10.1098\/rsta.2017.0237","article-title":"Blessing of dimensionality: Mathematical foundations of the statistical physics of data","volume":"376","author":"Gorban","year":"2018","journal-title":"Philos. Trans. R. Soc. A"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Tyukin, I.Y., Gorban, A.N., Alkhudaydi, M.H., and Zhou, Q. (2021). Demystification of few-shot and one-shot learning. arXiv.","DOI":"10.1109\/IJCNN52387.2021.9534395"},{"key":"ref_27","unstructured":"Warwick, K., and K\u00e1rn\u00fd, M. (1997). Utilizing geometric anomalies of high dimension: When complexity makes computation easier. Computer-Intensive Methods in Control and Signal Processing: The Curse of Dimensionality, Springer."},{"key":"ref_28","unstructured":"Donoho, D.L. (2000, January 6\u201312). High-Dimensional Data Analysis: The Curses and Blessings of Dimensionality. Proceedings of the Invited Lecture at Mathematical Challenges of the 21st Century, AMS National Meeting, Los Angeles, CA, USA. Available online: http:\/\/citeseerx.ist.psu.edu\/viewdoc\/summary?doi=10.1.1.329.3392."},{"key":"ref_29","first-page":"1135","article-title":"The More, the Merrier: The Blessing of Dimensionality for Learning Large Gaussian Mixtures","volume":"Volume 35","author":"Balcan","year":"2014","journal-title":"Proceedings of the 27th Conference on Learning Theory"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1016\/j.ifacol.2016.10.755","article-title":"The blessing of dimensionality: Separation theorems in the thermodynamic limit","volume":"49","author":"Gorban","year":"2016","journal-title":"IFAC-PapersOnLine"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1016\/j.neunet.2017.07.014","article-title":"Stochastic separation theorems","volume":"94","author":"Gorban","year":"2017","journal-title":"Neural Netw."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1016\/j.ins.2018.07.040","article-title":"Correction of AI systems by linear discriminants: Probabilistic foundations","volume":"466","author":"Gorban","year":"2018","journal-title":"Inf. Sci."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1016\/j.plrev.2018.09.005","article-title":"The unreasonable effectiveness of small neural ensembles in high-dimensional brain","volume":"29","author":"Gorban","year":"2019","journal-title":"Phys. Life Rev."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1093\/biomet\/77.1.33","article-title":"Principal points","volume":"77","author":"Flury","year":"1990","journal-title":"Biometrika"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Olivas, E.S., Guererro, J.D.M., Sober, M.M., Benedito, J.R.M., and Lopes, A.J.S. (2010). Principal graphs and manifolds. Handbook of Research on Machine Learning Applications and Trends: Algorithms, Methods and Techniques, IGI Global.","DOI":"10.4018\/978-1-60566-766-9"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Tyukin, I.Y., Gorban, A.N., Grechuk, B., and Green, S. (2019, January 14\u201319). Kernel Stochastic Separation Theorems and Separability Characterizations of Kernel Classifiers. Proceedings of the 2019 International Joint Conference on Neural Networks (IJCNN), Budapest, Hungary.","DOI":"10.1109\/IJCNN.2019.8852278"},{"key":"ref_37","unstructured":"Jolliffe, I. (1993). Principal Component Analysis, Springer."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Gorban, A.N., K\u00e9gl, B., Wunsch, D., and Zinovyev, A. (2008). Principal Manifolds for Data Visualisation and Dimension Reduction, Springer.","DOI":"10.1007\/978-3-540-73750-6"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"1299","DOI":"10.1162\/089976698300017467","article-title":"Nonlinear Component Analysis as a Kernel Eigenvalue Problem","volume":"10","year":"1998","journal-title":"Neural Comput."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1142\/S0129065710002383","article-title":"Principal manifolds and graphs in practice: From molecular biology to dynamical systems","volume":"20","author":"Gorban","year":"2010","journal-title":"Int. J. Neural Syst."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1002\/aic.690370209","article-title":"Nonlinear principal component analysis using autoassociative neural networks","volume":"37","author":"Kramer","year":"1991","journal-title":"AIChE J."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1126\/science.1127647","article-title":"Reducing the dimensionality of data with neural networks","volume":"28","author":"Hinton","year":"2006","journal-title":"Science"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Gorban, A.N., Makarov, V.A., and Tyukin, I.Y. (2020). High-Dimensional Brain in a High-Dimensional World: Blessing of Dimensionality. Entropy, 22.","DOI":"10.3390\/e22010082"},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Vershynin, R. (2018). High-Dimensional Probability: An Introduction with Applications in Data Science, Cambridge University Press.","DOI":"10.1017\/9781108231596"},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Wainwright, M.J. (2019). High-Dimensional Statistics: A Non-Asymptotic Viewpoint, Cambridge University Press.","DOI":"10.1017\/9781108627771"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1006\/aima.2000.1949","article-title":"Concentration property on probability spaces","volume":"156","author":"Giannopoulos","year":"2000","journal-title":"Adv. Math."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"178","DOI":"10.1007\/s000390300004","article-title":"Isoperimetry of waists and concentration of maps","volume":"13","author":"Gromov","year":"2003","journal-title":"Geom. Funct. Anal."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Ledoux, M. (2005). The Concentration of Measure Phenomenon, AMS. Number 89 in Mathematical Surveys & Monographs;.","DOI":"10.1090\/surv\/089"},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Kreinovich, V., and Kosheleva, O. (2021). Limit Theorems as Blessing of Dimensionality: Neural-Oriented Overview. Entropy, 23.","DOI":"10.20944\/preprints202103.0410.v1"},{"key":"ref_50","unstructured":"Foxx, C. (2018). Face Recognition Police Tools Staggeringly Inaccurate. BBC News Technol., 15, Available online: http:\/\/www.bbc.co.uk\/news\/technology-44089161."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1109\/MSPEC.2019.8678513","article-title":"IBM Watson, heal thyself: How IBM overpromised and underdelivered on AI health care","volume":"56","author":"Strickland","year":"2019","journal-title":"IEEE Spectr."},{"key":"ref_52","unstructured":"Banerjee, D.N., and Chanda, S.S. (2020). AI Failures: A Review of Underlying Issues. arXiv."},{"key":"ref_53","unstructured":"(2021, August 12). Artificial Intelligence Incident Database (AIID). Available online: https:\/\/incidentdatabase.ai\/."},{"key":"ref_54","unstructured":"(2021, August 12). PartnershipOnAI\/aiid. Available online: https:\/\/github.com\/PartnershipOnAI\/aiid."},{"key":"ref_55","unstructured":"Tsymbal, A. (2021, August 12). The Problem of Concept Drift: Definitions and Related Work. Available online: https:\/\/www.scss.tcd.ie\/publications\/tech-reports\/reports.04\/TCD-CS-2004-15.pdf."},{"key":"ref_56","doi-asserted-by":"crossref","first-page":"49","DOI":"10.3389\/fnbot.2018.00049","article-title":"Knowledge transfer between Artificial Intelligence systems","volume":"12","author":"Tyukin","year":"2018","journal-title":"Front. Neurorobot."},{"key":"ref_57","unstructured":"Arkad\u2019ev, A.G., and Braverman, E.M. (1967). Computers and Pattern Recognition, Thompson Book Company."},{"key":"ref_58","unstructured":"Perneel, C. (1999). Compactness and complexity of pattern recognition problems. Proceedings of the International Symposium on Pattern Recognition \u201cIn Memoriam Pierre Devijver\u201d, Royal Military Academy."},{"key":"ref_59","doi-asserted-by":"crossref","first-page":"391","DOI":"10.1016\/j.jfranklin.2004.03.001","article-title":"Replacing points by compacta in neural network approximation","volume":"341","author":"Kainen","year":"2004","journal-title":"J. Frankl. Inst."},{"key":"ref_60","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1186\/s40537-021-00469-z","article-title":"Unsupervised outlier detection in multidimensional data","volume":"8","author":"Belhaouari","year":"2021","journal-title":"J. Big Data"},{"key":"ref_61","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1016\/0893-9659(93)90023-G","article-title":"Quasiorthogonal dimension of Euclidian spaces","volume":"6","author":"Kainen","year":"1993","journal-title":"Appl. Math. Lett."},{"key":"ref_62","doi-asserted-by":"crossref","unstructured":"Kosheleva, O., Shary, S.P., Xiang, G., and Zapatrin, R. (2020). Quasiorthogonal dimension. Beyond Traditional Probabilistic Data Processing Techniques: Interval, Fuzzy etc. Methods and Their Applications, Springer.","DOI":"10.1007\/978-3-030-31041-7"},{"key":"ref_63","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1016\/j.ins.2015.09.021","article-title":"Approximation with random bases: Pro et contra","volume":"364\u2013365","author":"Gorban","year":"2016","journal-title":"Inf. Sci."},{"key":"ref_64","doi-asserted-by":"crossref","first-page":"2945","DOI":"10.1016\/S0031-3203(03)00176-6","article-title":"Data dimensionality estimation methods: A survey","volume":"36","author":"Camastra","year":"2003","journal-title":"Pattern Recognit."},{"key":"ref_65","doi-asserted-by":"crossref","first-page":"110","DOI":"10.3389\/fnbot.2019.00110","article-title":"Lizard brain: Tackling locally low-dimensional yet globally complex organization of multi-dimensional datasets","volume":"13","author":"Bac","year":"2020","journal-title":"Front. Neurorobot."},{"key":"ref_66","doi-asserted-by":"crossref","unstructured":"Albergante, L., Mirkes, E., Bac, J., Chen, H., Martin, A., Faure, L., Barillot, E., Pinello, L., Gorban, A., and Zinovyev, A. (2020). Robust and Scalable Learning of Complex Intrinsic Dataset Geometry via ElPiGraph. Entropy, 22.","DOI":"10.3390\/e22030296"},{"key":"ref_67","doi-asserted-by":"crossref","first-page":"33922","DOI":"10.1038\/srep33922","article-title":"Fluorescence-based assay as a new screening tool for toxic chemicals","volume":"6","author":"Moczko","year":"2016","journal-title":"Sci. Rep."},{"key":"ref_68","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1016\/S0165-0114(97)00077-8","article-title":"Towards a theory of fuzzy information granulation and its centrality in human reasoning and fuzzy logic","volume":"19","author":"Zadeh","year":"1997","journal-title":"Fuzzy Sets Syst."},{"key":"ref_69","doi-asserted-by":"crossref","unstructured":"Pedrycz, W., Skowron, A., and Kreinovich, V. (2008). Handbook of Granular Computing, John Wiley & Sons.","DOI":"10.1002\/9780470724163"},{"key":"ref_70","doi-asserted-by":"crossref","first-page":"1043","DOI":"10.1007\/s00039-011-0136-5","article-title":"Interpolating thin-shell and sharp large-deviation estimates for lsotropic log-concave measures","volume":"21","author":"Milman","year":"2011","journal-title":"Geom. Funct. Anal."},{"key":"ref_71","unstructured":"L\u00e9vy, P. (1951). Probl\u00e8mes Concrets D\u2019analyse Fonctionnelle, Gauthier-Villars."},{"key":"ref_72","unstructured":"Khinchin, A.Y. (1949). Mathematical Foundations of Statistical Mechanics, Courier Corporation."},{"key":"ref_73","doi-asserted-by":"crossref","unstructured":"Thompson, C.J. (2015). Mathematical Statistical Mechanics, Princeton University Press.","DOI":"10.1515\/9781400868681"},{"key":"ref_74","unstructured":"Kolmogorov, A.N. (2018). Foundations of the Theory of Probability, Courier Dover Publications. [2nd ed.]."},{"key":"ref_75","doi-asserted-by":"crossref","first-page":"567","DOI":"10.1016\/j.ins.2014.06.030","article-title":"Evolutionary compact embedding for large-scale image classification","volume":"316","author":"Liu","year":"2015","journal-title":"Inf. Sci."},{"key":"ref_76","doi-asserted-by":"crossref","unstructured":"Vemulapalli, R., and Agarwala, A. (2019, January 15\u201320). A Compact Embedding for Facial Expression Similarity. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA. Available online: https:\/\/openaccess.thecvf.com\/content_CVPR_2019\/html\/Vemulapalli_A_Compact_Embedding_for_Facial_Expression_Similarity_CVPR_2019_paper.html.","DOI":"10.1109\/CVPR.2019.00583"},{"key":"ref_77","doi-asserted-by":"crossref","unstructured":"Bhattarai, B., Liu, H., and Huang, H.H. (July, January 30). Ceci: Compact embedding cluster index for scalable subgraph matching. Proceedings of the 2019 International Conference on Management of Data, Amsterdam, The Netherlands.","DOI":"10.1145\/3299869.3300086"},{"key":"ref_78","doi-asserted-by":"crossref","unstructured":"Tyukin, I.Y., Higham, D.J., and Gorban, A.N. (2020, January 19\u201324). On adversarial examples and stealth attacks in Artificial Intelligence systems. Proceedings of the 2020 International Joint Conference on Neural Networks (IJCNN), Glasgow, UK.","DOI":"10.1109\/IJCNN48605.2020.9207472"},{"key":"ref_79","unstructured":"Tyukin, I.Y., Higham, D.J., Woldegeorgis, E., and Gorban, A.N. (2021). The Feasibility and Inevitability of Stealth Attacks. arXiv."},{"key":"ref_80","doi-asserted-by":"crossref","unstructured":"Colbrook, M.J., Antun, V., and Hansen, A.C. (2021). Can stable and accurate neural networks be computed?\u2014On the barriers of deep learning and Smale\u2019s 18th problem. arXiv.","DOI":"10.1073\/pnas.2107151119"},{"key":"ref_81","unstructured":"Rudin, W. (1991). Functional Analysis, McGraw-Hill."},{"key":"ref_82","doi-asserted-by":"crossref","unstructured":"Xu, R., and Wunsch, D. (2008). Clustering, John Wiley & Sons.","DOI":"10.1002\/9780470382776"},{"key":"ref_83","doi-asserted-by":"crossref","first-page":"124","DOI":"10.1016\/j.ins.2021.01.022","article-title":"Blessing of dimensionality at the edge and geometry of few-shot learning","volume":"564","author":"Tyukin","year":"2021","journal-title":"Inf. Sci."},{"key":"ref_84","doi-asserted-by":"crossref","first-page":"305","DOI":"10.1016\/S0165-0114(01)00191-9","article-title":"Unsupervised fuzzy clustering with multi-center clusters","volume":"128","author":"Tao","year":"2002","journal-title":"Fuzzy Sets Syst."},{"key":"ref_85","unstructured":"Krizhevsky, A. (2009). Learning Multiple Layers of Features from Tiny Images. [Master\u2019s Thesis, University of Toronto]. Available online: https:\/\/citeseerx.ist.psu.edu\/viewdoc\/versions?doi=10.1.1.222.9220."},{"key":"ref_86","unstructured":"Krizhevsky, A. (2021, August 12). CIFAR 10 Dataset. Available online: https:\/\/www.cs.toronto.edu\/~kriz\/cifar.html."},{"key":"ref_87","doi-asserted-by":"crossref","unstructured":"Ma, R., Wang, Y., and Cheng, L. (2020, January 19). Feature selection on data stream via multi-cluster structure preservation. Proceedings of the 29th ACM International Conference on Information and Knowledge Management, Online.","DOI":"10.1145\/3340531.3411928"},{"key":"ref_88","doi-asserted-by":"crossref","unstructured":"Cai, D., Zhang, C., and He, X. (2010, January 24\u201328). Unsupervised feature selection for multi-cluster data. Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Washington, DC, USA.","DOI":"10.1145\/1835804.1835848"},{"key":"ref_89","unstructured":"Gasparovic, E., and Domeniconi, C. (2019). The hubness phenomenon in high-dimensional spaces. Research in Data Science, Springer."},{"key":"ref_90","doi-asserted-by":"crossref","first-page":"107","DOI":"10.2307\/1968691","article-title":"\u00dcber die beste Annaherung von Funktionen einer gegebenen Funktionenklasse","volume":"37","author":"Kolmogoroff","year":"1936","journal-title":"Ann. Math."},{"key":"ref_91","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1070\/RM1960v015n03ABEH004093","article-title":"Diameters of sets in function spaces and the theory of best approximations","volume":"15","author":"Tikhomirov","year":"1960","journal-title":"Russ. Math. Surv."},{"key":"ref_92","doi-asserted-by":"crossref","first-page":"965","DOI":"10.1007\/s10208-013-9149-9","article-title":"N-widths and \u03b5-dimensions for high-dimensional approximations","volume":"13","author":"Dung","year":"2013","journal-title":"Found. Comput. Math."},{"key":"ref_93","doi-asserted-by":"crossref","first-page":"388","DOI":"10.1007\/s12559-019-09667-7","article-title":"How deep should be the depth of convolutional neural networks: A backyard dog case study","volume":"12","author":"Gorban","year":"2020","journal-title":"Cogn. Comput."},{"key":"ref_94","doi-asserted-by":"crossref","unstructured":"Cerquitelli, T., Proto, S., Ventura, F., Apiletti, D., and Baralis, E. (2019, January 26). Towards a real-time unsupervised estimation of predictive model degradation. Proceedings of the Real-Time Business Intelligence and Analytics, Los Angeles, CA, USA.","DOI":"10.1145\/3350489.3350494"},{"key":"ref_95","doi-asserted-by":"crossref","first-page":"134","DOI":"10.1016\/j.envsoft.2012.03.012","article-title":"Good practice in Bayesian network modelling","volume":"37","author":"Chen","year":"2012","journal-title":"Environ. Model. Softw."},{"key":"ref_96","doi-asserted-by":"crossref","unstructured":"Lucas, P., G\u00e1mez, J.A., and Salmer\u00f3n, A. (2007). Bayesian Network Models with Discrete and Continuous Variables. Advances in Probabilistic Graphical Models. Studies in Fuzziness and Soft Computing, Springer.","DOI":"10.1007\/978-3-540-68996-6"},{"key":"ref_97","unstructured":"Rezende, D.J., Mohamed, S., and Wierstra, D. (2014, January 21\u201326). Stochastic backpropagation and approximate inference in deep generative models. Proceedings of the 31st International Conference on Machine Learning, Beijing, China."},{"key":"ref_98","first-page":"599","article-title":"A Practical Guide to Training Restricted Boltzmann Machines","volume":"Volume 7700","author":"Montavon","year":"2012","journal-title":"Neural Networks: Tricks of the Trade"},{"key":"ref_99","doi-asserted-by":"crossref","first-page":"1135","DOI":"10.1038\/nbt1209-1135","article-title":"How does multiple testing correction work?","volume":"27","author":"Noble","year":"2009","journal-title":"Nat. Biotechnol."},{"key":"ref_100","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1378\/chest.11-0523","article-title":"Correction for multiple testing: Is there a resolution?","volume":"140","author":"Streiner","year":"2011","journal-title":"Chest"},{"key":"ref_101","doi-asserted-by":"crossref","unstructured":"Sompairac, N., Nazarov, P.V., Czerwinska, U., Cantini, L., Biton, A., Molkenov, A., Zhumadilov, Z., Barillot, E., Radvanyi, F., and Gorban, A. (2019). Independent component analysis for unraveling the complexity of cancer omics datasets. Int. J. Mol. Sci., 20.","DOI":"10.3390\/ijms20184414"},{"key":"ref_102","doi-asserted-by":"crossref","first-page":"562","DOI":"10.1093\/biostatistics\/kxx053","article-title":"Missing data and technical variability in single-cell RNA-sequencing experiments","volume":"19","author":"Hicks","year":"2018","journal-title":"Biostatistics"},{"key":"ref_103","doi-asserted-by":"crossref","first-page":"1525","DOI":"10.1101\/gr.138115.112","article-title":"Copy number variation detection and genotyping from exome sequence data","volume":"22","author":"Krumm","year":"2012","journal-title":"Genome Res."},{"key":"ref_104","doi-asserted-by":"crossref","first-page":"459","DOI":"10.1109\/TVCG.2004.17","article-title":"Robust linear dimensionality reduction","volume":"10","author":"Koren","year":"2004","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"key":"ref_105","unstructured":"Mirkes, E.M., Gorban, A.N., and Zinoviev, A. (2021, August 12). Supervised PCA. Available online: https:\/\/github.com\/Mirkes\/SupervisedPCA."},{"key":"ref_106","doi-asserted-by":"crossref","first-page":"2789","DOI":"10.1016\/j.patcog.2008.01.001","article-title":"A unified framework for semi-supervised dimensionality reduction","volume":"41","author":"Song","year":"2008","journal-title":"Pattern Recognit."},{"key":"ref_107","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1186\/1745-6150-2-2","article-title":"Component retention in principal component analysis with application to cDNA microarray data","volume":"2","author":"Cangelosi","year":"2007","journal-title":"Biol. Direct"},{"key":"ref_108","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1007\/s10994-009-5152-4","article-title":"A theory of learning from different domains","volume":"79","author":"Blitzer","year":"2010","journal-title":"Mach. Learn."},{"key":"ref_109","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1016\/j.inffus.2014.12.003","article-title":"A survey of multi-source domain adaptation","volume":"24","author":"Sun","year":"2015","journal-title":"Inf. Fusion"},{"key":"ref_110","doi-asserted-by":"crossref","unstructured":"Saito, K., Watanabe, K., Ushiku, Y., and Harada, T. (2018, January 18\u201323). Maximum classifier discrepancy for unsupervised domain adaptation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00392"},{"key":"ref_111","first-page":"2096","article-title":"Domain-adversarial training of neural networks","volume":"17","author":"Ganin","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref_112","doi-asserted-by":"crossref","first-page":"81800F","DOI":"10.1117\/12.898229","article-title":"Transfer component analysis for domain adaptation in image classification","volume":"Volume 8180","author":"Matasci","year":"2011","journal-title":"Image and Signal Processing for Remote Sensing XVII"},{"key":"ref_113","doi-asserted-by":"crossref","first-page":"1427","DOI":"10.1016\/j.camwa.2012.09.011","article-title":"Is the k-NN classifier in high dimensions affected by the curse of dimensionality?","volume":"65","author":"Pestov","year":"2013","journal-title":"Comput. Math. Appl."},{"key":"ref_114","doi-asserted-by":"crossref","unstructured":"Mirkes, E.M., Allohibi, J., and Gorban, A.N. (2020). Fractional Norms and Quasinorms Do Not Help to Overcome the Curse of Dimensionality. Entropy, 22.","DOI":"10.3390\/e22101105"},{"key":"ref_115","doi-asserted-by":"crossref","unstructured":"Golubitsky, M., and Guillemin, V. (1974). Stable Mappings and Their Singularities, Springer.","DOI":"10.1007\/978-1-4615-7904-5"},{"key":"ref_116","doi-asserted-by":"crossref","first-page":"956","DOI":"10.2307\/2373413","article-title":"The closing lemma","volume":"89","author":"Pugh","year":"1967","journal-title":"Am. J. Math."},{"key":"ref_117","doi-asserted-by":"crossref","unstructured":"Palis, J., and de Melo, W. (1982). The Kupka-Smale Theorem. Geometric Theory of Dynamical Systems, Springer.","DOI":"10.1007\/978-1-4612-5703-5"},{"key":"ref_118","unstructured":"Oxtoby, J.C. (2013). Measure and Category: A Survey of the Analogies between Topological and Measure Spaces, Springer."},{"key":"ref_119","unstructured":"Gorban, A.N. (1984). Equilibrium Encircling. Equations of Chemical Kinetics and Their Thermodynamic Analysis, Nauka."},{"key":"ref_120","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1051\/mmnp:2008024","article-title":"Selection Theorem for Systems with Inheritance","volume":"2","author":"Gorban","year":"2007","journal-title":"Math. Model. Nat. Phenom."}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/23\/8\/1090\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T06:49:01Z","timestamp":1760165341000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/23\/8\/1090"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,22]]},"references-count":120,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2021,8]]}},"alternative-id":["e23081090"],"URL":"https:\/\/doi.org\/10.3390\/e23081090","relation":{"has-preprint":[{"id-type":"doi","id":"10.20944\/preprints202106.0718.v1","asserted-by":"object"}]},"ISSN":["1099-4300"],"issn-type":[{"value":"1099-4300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,8,22]]}}}