{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T11:18:25Z","timestamp":1784891905138,"version":"3.55.0"},"reference-count":84,"publisher":"Springer Science and Business Media LLC","issue":"5-6","license":[{"start":{"date-parts":[[2021,1,22]],"date-time":"2021-01-22T00:00:00Z","timestamp":1611273600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,1,22]],"date-time":"2021-01-22T00:00:00Z","timestamp":1611273600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100012652","name":"ETH Z\u00fcrich Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012652","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Ann Math Artif Intell"],"published-print":{"date-parts":[[2021,6]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>The universal approximation property of various machine learning models is currently only understood on a case-by-case basis, limiting the rapid development of new theoretically justified neural network architectures and blurring our understanding of our current models\u2019 potential. This paper works towards overcoming these challenges by presenting a characterization, a representation, a construction method, and an existence result, each of which applies to any universal approximator on most function spaces of practical interest. Our characterization result is used to describe which activation functions allow the feed-forward architecture to maintain its universal approximation capabilities when multiple constraints are imposed on its final layers and its remaining layers are only sparsely connected. These include a rescaled and shifted Leaky ReLU activation function but not the ReLU activation function. Our construction and representation result is used to exhibit a simple modification of the feed-forward architecture, which can approximate any continuous function with non-pathological growth, uniformly on the entire Euclidean input space. This improves the known capabilities of the feed-forward architecture.<\/jats:p>","DOI":"10.1007\/s10472-020-09723-1","type":"journal-article","created":{"date-parts":[[2021,1,22]],"date-time":"2021-01-22T09:08:48Z","timestamp":1611306528000},"page":"435-469","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":68,"title":["The Universal Approximation Property"],"prefix":"10.1007","volume":"89","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6791-3371","authenticated-orcid":false,"given":"Anastasis","family":"Kratsios","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,1,22]]},"reference":[{"key":"9723_CR1","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1007\/BF02478259","volume":"5","author":"WS McCulloch","year":"1943","unstructured":"McCulloch, W.S., Pitts, W.: A logical calculus of the ideas immanent in nervous activity. Bull. Math. Biophys. 5, 115\u2013133 (1943)","journal-title":"Bull. Math. Biophys."},{"issue":"6","key":"9723_CR2","doi-asserted-by":"publisher","first-page":"386","DOI":"10.1037\/h0042519","volume":"65","author":"F Rosenblatt","year":"1958","unstructured":"Rosenblatt, F.: The perceptron: a probabilistic model for information storage and organization in the brain. Psych. Rev. 65(6), 386 (1958)","journal-title":"Psych. Rev."},{"issue":"5","key":"9723_CR3","doi-asserted-by":"publisher","first-page":"551","DOI":"10.1016\/0893-6080(90)90005-6","volume":"3","author":"K Hornik","year":"1990","unstructured":"Hornik, K., Stinchcombe, M., White, H.: Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networks. Neural Netw. 3(5), 551\u2013560 (1990)","journal-title":"Neural Netw."},{"issue":"4","key":"9723_CR4","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/BF02551274","volume":"2","author":"G Cybenko","year":"1989","unstructured":"Cybenko, G.: Approximation by superpositions of a sigmoidal function. Math. Control Signals Syst. 2(4), 303\u2013314 (1989)","journal-title":"Math. Control Signals Syst."},{"issue":"2","key":"9723_CR5","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1016\/0893-6080(91)90009-T","volume":"4","author":"K Hornik","year":"1991","unstructured":"Hornik, K.: Approximation capabilities of multilayer feedforward networks. Neural Netw. 4(2), 251\u2013257 (1991)","journal-title":"Neural Netw."},{"key":"9723_CR6","first-page":"953","volume":"114","author":"AN Kolmogorov","year":"1957","unstructured":"Kolmogorov, A.N.: On the representation of continuous functions of many variables by superposition of continuous functions of one variable and addition. Dokl. Akad. Nauk SSSR 114, 953\u2013956 (1957)","journal-title":"Dokl. Akad. Nauk SSSR"},{"key":"9723_CR7","doi-asserted-by":"crossref","unstructured":"Webb, S.: Deep learning for biology. Nature 554(7693) (2018)","DOI":"10.1038\/d41586-018-02174-z"},{"issue":"7","key":"9723_CR8","doi-asserted-by":"publisher","first-page":"389","DOI":"10.1038\/s41576-019-0122-6","volume":"20","author":"G Eraslan","year":"2019","unstructured":"Eraslan, G., Avsec, Z., Gagneur, J., Theis, F.J.: Deep learning: new computational modelling techniques for genomics. Nat. Rev. Genet. 20(7), 389\u2013403 (2019)","journal-title":"Nat. Rev. Genet."},{"key":"9723_CR9","doi-asserted-by":"publisher","first-page":"229","DOI":"10.3389\/fnins.2014.00229","volume":"8","author":"SM Plis","year":"2014","unstructured":"Plis, S.M.: Deep learning for neuroimaging: a validation study. Front. Neurosci. 8, 229 (2014)","journal-title":"Front. Neurosci."},{"key":"9723_CR10","doi-asserted-by":"crossref","unstructured":"Zhang, W.E., Sheng, Q.Z., Alhazmi, A., Li, C.: Adversarial attacks on deep-learning models in natural language processing: A survey. ACM Trans. Intell. Syst. Technol. 11(3) (2020)","DOI":"10.1145\/3374217"},{"issue":"8","key":"9723_CR11","doi-asserted-by":"publisher","first-page":"1271","DOI":"10.1080\/14697688.2019.1571683","volume":"19","author":"H Buehler","year":"2019","unstructured":"Buehler, H., Gonon, L., Teichmann, J., Wood, B.: Deep hedging. Quant. Finance 19(8), 1271\u20131291 (2019)","journal-title":"Quant. Finance"},{"key":"9723_CR12","first-page":"Paper No. 74, 2","volume":"20","author":"S Becker","year":"2019","unstructured":"Becker, S., Cheridito, P., Jentzen, A.: Deep optimal stopping. J. Mach. Learn. Res. 20, Paper No. 74, 25 (2019)","journal-title":"J. Mach. Learn. Res."},{"issue":"4","key":"9723_CR13","doi-asserted-by":"publisher","first-page":"101","DOI":"10.3390\/risks8040101","volume":"8","author":"C Cuchiero","year":"2020","unstructured":"Cuchiero, C., Khosrawi, W., Teichmann, J.: A generative adversarial network approach to calibration of local stochastic volatility models. Risks 8(4), 101 (2020)","journal-title":"Risks"},{"issue":"2","key":"9723_CR14","doi-asserted-by":"publisher","first-page":"40","DOI":"10.3390\/risks8020040","volume":"8","author":"A Kratsios","year":"2020","unstructured":"Kratsios, A., Hyndman, C.: Deep arbitrage-free learning in a generalized HJM framework via arbitrage-regularization. Risks 8(2), 40 (2020)","journal-title":"Risks"},{"issue":"0","key":"9723_CR15","first-page":"1","volume":"0","author":"B Horvath","year":"2020","unstructured":"Horvath, B., Muguruza, A., Tomas, M.: Deep learning volatility: a deep neural network perspective on pricing and calibration in (rough) volatility models. Quant. Finance 0(0), 1\u201317 (2020)","journal-title":"Quant. Finance"},{"issue":"6","key":"9723_CR16","doi-asserted-by":"publisher","first-page":"861","DOI":"10.1016\/S0893-6080(05)80131-5","volume":"6","author":"M Leshno","year":"1993","unstructured":"Leshno, M., Lin, V.Y., Pinkus, A., Schocken, S.: Multilayer feedforward networks with a nonpolynomial activation function can approximate any function. Neural Netw. 6(6), 861\u2013867 (1993)","journal-title":"Neural Netw."},{"key":"9723_CR17","unstructured":"Kidger, P., Lyons, T. In: Abernethy, J, Agarwal, S (eds.) : Universal Approximation with Deep Narrow Networks, vol. 125, pp 2306\u20132327. PMLR, USA (2020)"},{"issue":"5","key":"9723_CR18","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1016\/0893-6080(89)90020-8","volume":"2","author":"K Hornik","year":"1989","unstructured":"Hornik, K., Stinchcombe, M., White, H.: Multilayer feedforward networks are universal approximators. Neural Netw. 2(5), 359\u2013366 (1989)","journal-title":"Neural Netw."},{"key":"9723_CR19","unstructured":"Park, S., Yun, C., Lee, J., Shin, J.: Minimum width for universal approximation. ICLR (2021)"},{"key":"9723_CR20","doi-asserted-by":"crossref","unstructured":"Hanin, B.: Universal function approximation by deep neural nets with bounded width and relu activations. Math. - MDPI 7(10) (2019)","DOI":"10.3390\/math7100992"},{"key":"9723_CR21","unstructured":"Lu, Z., Pu, H., Wang, F., Hu, Z., Wang, L.: The expressive power of neural networks: A view from the width. In: Advances in Neural Information Processing Systems, vol. 30, pp 6231\u20136239. Curran Associates, Inc. (2017)"},{"issue":"1","key":"9723_CR22","doi-asserted-by":"publisher","first-page":"S143","DOI":"10.1016\/j.neuroimage.2008.10.052","volume":"45","author":"PT Fletcher","year":"2009","unstructured":"Fletcher, P.T., Venkatasubramanian, S., Joshi, S.: The geometric median on riemannian manifolds with application to robust atlas estimation. Neuroimage 45(1), S143\u2013S152 (2009). Mathematics in Brain Imaging","journal-title":"Neuroimage"},{"issue":"1","key":"9723_CR23","first-page":"cnaa002, 18","volume":"8","author":"M Keller-Ressel","year":"2020","unstructured":"Keller-Ressel, M., Nargang, S.: Hydra: a method for strain-minimizing hyperbolic embedding of network- and distance-based data. J. Complex Netw. 8(1), cnaa002, 18 (2020)","journal-title":"J. Complex Netw."},{"key":"9723_CR24","unstructured":"Ganea, O., Becigneul, G., Hofmann, T.: Hyperbolic neural networks. In: Bengio, S, Wallach, H, Larochelle, H, Grauman, K, Cesa-Bianchi, N, Garnett, R (eds.) Advances in Neural Information Processing Systems, vol. 31, pp 5345\u20135355. Curran Associates, Inc. (2018)"},{"key":"9723_CR25","unstructured":"Zhang, H., Goodfellow, I., Metaxas, D., Odena, A.: Self-attention generative adversarial networks. In: International Conference on Machine Learning, pp 7354\u20137363. PMLR (2019)"},{"key":"9723_CR26","doi-asserted-by":"publisher","first-page":"397","DOI":"10.2140\/pjm.1956.6.397","volume":"6","author":"RF Arens","year":"1956","unstructured":"Arens, R.F., Eells, J.: On embedding uniform and topological spaces. Pacific J. Math. 6, 397\u2013403 (1956)","journal-title":"Pacific J. Math."},{"key":"9723_CR27","first-page":"669","volume":"5","author":"U von Luxburg","year":"2003","unstructured":"von Luxburg, U., Bousquet, O.: Distance-based classification with Lipschitz functions. J. Mach. Learn. Res. 5, 669\u2013695 (2003\/04)","journal-title":"J. Mach. Learn. Res."},{"key":"9723_CR28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1515\/crelle-2018-0037","volume":"764","author":"L Ambrosio","year":"2020","unstructured":"Ambrosio, L., Puglisi, D.: Linear extension operators between spaces of Lipschitz maps and optimal transport. J. Reine Angew. Math. 764, 1\u201321 (2020)","journal-title":"J. Reine Angew. Math."},{"key":"9723_CR29","unstructured":"Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein generative adversarial networks, pp. 214\u2013223. PMLR, International Convention Centre, Sydney, Australia (2017)"},{"key":"9723_CR30","unstructured":"Xu, T., Le, W., Munn, M., Acciaio, B.: Cot-gan: Generating sequential data via causal optimal transport. Advances in Neural Information Processing Systems 33 (2020)"},{"key":"9723_CR31","doi-asserted-by":"crossref","unstructured":"Godefroy, G., Kalton, N.J.: Lipschitz-free Banach spaces. pp. 121\u2013141. Dedicated to Professor Aleksander Pe\u0142czy\u0144ski on the occasion of his 70th birthday (2003)","DOI":"10.4064\/sm159-1-6"},{"key":"9723_CR32","doi-asserted-by":"crossref","unstructured":"Weaver, N.: Lipschitz algebras. World Scientific Publishing Co. Pte. Ltd., Hackensack (2018)","DOI":"10.1142\/9911"},{"issue":"2","key":"9723_CR33","first-page":"89","volume":"55","author":"G Godefroy","year":"2015","unstructured":"Godefroy, G.: A survey on Lipschitz-free Banach spaces. Comment. Math. 55(2), 89\u2013118 (2015)","journal-title":"Comment. Math."},{"key":"9723_CR34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-21298-7","volume-title":"Riemannian Geometry and Geometric Analysis","author":"J Jost","year":"2011","unstructured":"Jost, J.: Riemannian Geometry and Geometric Analysis, 6th edn. Universitext, Springer, Heidelberg (2011)","edition":"6th edn."},{"key":"9723_CR35","unstructured":"Basso, G.: Extending and improving conical bicombings. preprint 2005.13941 (2020)"},{"key":"9723_CR36","volume-title":"Modern general topology","author":"J- Nagata","year":"1974","unstructured":"Nagata, J-: Modern general topology, revised. North-Holland Publishing Co., Amsterdam (1974). Wolters-Noordhoff Publishing, Groningen; American Elsevier Publishing Co., New York (1974). Bibliotheca Mathematica, Vol. VII","edition":"revised"},{"key":"9723_CR37","volume-title":"Topology","author":"JR Munkres","year":"2000","unstructured":"Munkres, J.R.: Topology. Prentice Hall, Inc., Upper Saddle River (2000). 2"},{"key":"9723_CR38","first-page":"2651","volume":"7","author":"CA Micchelli","year":"2006","unstructured":"Micchelli, C.A., Xu, Y., Zhang, H.: Universal kernels. J. Mach. Learn. Res. 7, 2651\u20132667 (2006)","journal-title":"J. Mach. Learn. Res."},{"key":"9723_CR39","first-page":"1095","volume":"10","author":"L Kontorovich","year":"2009","unstructured":"Kontorovich, L., Nadler, B.: Universal kernel-based learning with applications to regular languages. J. Mach. Learn. Res. 10, 1095\u20131129 (2009)","journal-title":"J. Mach. Learn. Res."},{"key":"9723_CR40","first-page":"1615","volume":"9","author":"A Caponnetto","year":"2008","unstructured":"Caponnetto, A., Micchelli, C.A., Pontil, M., Ying, Y.: Universal multi-task kernels. J. Mach. Learn. Res. 9, 1615\u20131646 (2008)","journal-title":"J. Mach. Learn. Res."},{"key":"9723_CR41","first-page":"Paper No. 179,","volume":"20","author":"L Grigoryeva","year":"2019","unstructured":"Grigoryeva, L., Ortega, J-P: Differentiable reservoir computing. J. Mach. Learn. Res. 20, Paper No. 179, 62 (2019)","journal-title":"J. Mach. Learn. Res."},{"key":"9723_CR42","unstructured":"Cuchiero, C., Gonon, L., Grigoryeva, L., Ortega, J-P, Teichmann, J.: Discrete-time signatures and randomness in reservoir computing. pre-print 2010.14615 (2020)"},{"issue":"2","key":"9723_CR43","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1007\/s11263-012-0591-y","volume":"105","author":"PT Fletcher","year":"2013","unstructured":"Fletcher, P.T.: Geodesic regression and the theory of least squares on Riemannian manifolds. Int. J. Comput. Vis. 105(2), 171\u2013185 (2013)","journal-title":"Int. J. Comput. Vis."},{"key":"9723_CR44","unstructured":"Kratsios, A., Bilokopytov, E.: Non-euclidean universal approximation (2020)"},{"key":"9723_CR45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-02045-7","volume-title":"Locally convex spaces, Graduate Texts in Mathematics, vol. 269","author":"MS Osborne","year":"2014","unstructured":"Osborne, M.S.: Locally convex spaces, Graduate Texts in Mathematics, vol. 269. Springer, Cham (2014)"},{"key":"9723_CR46","doi-asserted-by":"publisher","unstructured":"Petersen, P., Raslan, M., Voigtlaender, F.: Topological properties of the set of functions generated by neural networks of fixed size. Found Comput Math. https:\/\/doi.org\/10.1007\/s10208-020-09461-0 (2020)","DOI":"10.1007\/s10208-020-09461-0"},{"key":"9723_CR47","doi-asserted-by":"crossref","unstructured":"Gribonval, R., Kutyniok, G., Nielsen, M., Voigtlaender, F.: Approximation spaces of deep neural networks. Constr. Approx forthcoming (2020)","DOI":"10.1007\/s00365-021-09543-4"},{"key":"9723_CR48","unstructured":"Goodfellow, I., Bengio, Y., Courville, A.: Deep learning. Adaptive Computation and Machine Learning. MIT Press, Cambridge (2016)"},{"issue":"51","key":"9723_CR49","first-page":"3","volume":"9","author":"I Gelfand","year":"1941","unstructured":"Gelfand, I.: Normierte Ringe. Rec. Math. N. S. 9(51), 3\u201324 (1941)","journal-title":"Rec. Math. N. S."},{"key":"9723_CR50","doi-asserted-by":"publisher","first-page":"619","DOI":"10.1090\/S0002-9904-1966-11541-0","volume":"72","author":"JR Isbell","year":"1966","unstructured":"Isbell, J.R.: Structure of categories. Bull. Amer. Math. Soc. 72, 619\u2013655 (1966)","journal-title":"Bull. Amer. Math. Soc."},{"issue":"3-4","key":"9723_CR51","doi-asserted-by":"publisher","first-page":"255","DOI":"10.5486\/PMD.2012.4814","volume":"80","author":"GD Dimov","year":"2012","unstructured":"Dimov, G.D.: Some generalizations of the Stone duality theorem. Publ. Math. Debrecen 80(3-4), 255\u2013293 (2012)","journal-title":"Publ. Math. Debrecen"},{"key":"9723_CR52","doi-asserted-by":"crossref","unstructured":"Tuitman, J.: A refinement of a mixed sparse effective Nullstellensatz. Int. Math. Res. Not. IMRN 7, 1560\u20131572 (2011)","DOI":"10.1093\/imrn\/rnq127"},{"issue":"2","key":"9723_CR53","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1007\/s11263-012-0591-y","volume":"105","author":"PT Fletcher","year":"2013","unstructured":"Fletcher, P.T.: Geodesic regression and the theory of least squares on Riemannian manifolds. Int. J. Comput. Vis. 105(2), 171\u2013185 (2013)","journal-title":"Int. J. Comput. Vis."},{"key":"9723_CR54","first-page":"593","volume":"12","author":"G Meyer","year":"2011","unstructured":"Meyer, G., Bonnabel, S., Sepulchre, R.: Regression on fixed-rank positive semidefinite matrices: a Riemannian approach. J. Mach. Learn. Res. 12, 593\u2013625 (2011)","journal-title":"J. Mach. Learn. Res."},{"key":"9723_CR55","unstructured":"Baes, M., Herrera, C., Neufeld, A., Ruyssen, P.: Low-rank plus sparse decomposition of covariance matrices using neural network parametrization. pre-print 1908.00461 (2019)"},{"key":"9723_CR56","doi-asserted-by":"publisher","first-page":"480","DOI":"10.1037\/0033-295X.99.3.480","volume":"99","author":"J Hummel","year":"1992","unstructured":"Hummel, J., Biederman, I.: Dynamic binding in a neural network for shape recognition. Psych. Rev. 99, 480\u2013517 (1992)","journal-title":"Psych. Rev."},{"key":"9723_CR57","unstructured":"Bishop, C.M.: Mixture density networks (1994)"},{"key":"9723_CR58","unstructured":"Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. ICLR (2017)"},{"issue":"1","key":"9723_CR59","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1109\/TNN.2008.2005605","volume":"20","author":"F Scarselli","year":"2009","unstructured":"Scarselli, F., Gori, M., Tsoi, A.C., Hagenbuchner, M., Monfardini, G.: The graph neural network model. Neural Netw. Learn Syst. 20(1), 61\u201380 (2009)","journal-title":"Neural Netw. Learn Syst."},{"key":"9723_CR60","unstructured":"PrajitRamachandran, Q.V.L.: Searching for activation functions. ICLR (2018)"},{"key":"9723_CR61","doi-asserted-by":"crossref","unstructured":"Pinkus, A.: Approximation theory of the MLP model in neural networks 8, 143\u2013195 (1999)","DOI":"10.1017\/S0962492900002919"},{"issue":"5","key":"9723_CR62","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1073\/pnas.17.5.315","volume":"17","author":"BO Koopman","year":"1931","unstructured":"Koopman, B.O.: Hamiltonian systems and transformation in hilbert space. Proc. Natl. Acad. Sci. 17(5), 315\u2013318 (1931)","journal-title":"Proc. Natl. Acad. Sci."},{"issue":"1","key":"9723_CR63","first-page":"3","volume":"30","author":"AL Maas","year":"2013","unstructured":"Maas, A.L., Hannun, A.Y., Ng, A.Y.: Rectifier nonlinearities improve neural network acoustic models. ICML 30(1), 3 (2013)","journal-title":"ICML"},{"key":"9723_CR64","volume-title":"Composition operators on function spaces, North-Holland Mathematics Studies, vol. 179","author":"RK Singh","year":"1993","unstructured":"Singh, R.K., Manhas, J.S.: Composition operators on function spaces, North-Holland Mathematics Studies, vol. 179. North-Holland Publishing Co., Amsterdam (1993)"},{"key":"9723_CR65","unstructured":"Bengio, Y.: Deep learning of representations for unsupervised and transfer learning. In: Proceedings of ICML Workshop on Unsupervised and Transfer Learning, vol. 27, pp 17\u201336. JMLR Workshop and Conference Proceedings (2012)"},{"key":"9723_CR66","unstructured":"Tan, C., Sun, F., Kong, T., Zhang, W., Yang, C., Liu, C.: A survey on deep transfer learning. In: K\u016frkov\u00e1, V., Manolopoulos, Y, Hammer, B, Iliadis, L, Maglogiannis, I (eds.) Artificial Neural Networks and Machine Learning \u2013 ICANN 2018, pp 270\u2013279. Springer (2018)"},{"key":"9723_CR67","unstructured":"Chollet, F., et al.: Keras. https:\/\/keras.io\/guides\/transfer_learning\/ (2015)"},{"issue":"3","key":"9723_CR68","doi-asserted-by":"publisher","first-page":"930","DOI":"10.1109\/18.256500","volume":"39","author":"AR Barron","year":"1993","unstructured":"Barron, A.R.: Universal approximation bounds for superpositions of a sigmoidal function. IEEE Trans. Inform. Theory 39(3), 930\u2013945 (1993)","journal-title":"IEEE Trans. Inform. Theory"},{"key":"9723_CR69","doi-asserted-by":"crossref","unstructured":"Darken, C., Donahue, M., Gurvits, L., Sontag, E.: Rate of approximation results motivated by robust neural network learning. In: Proceedings of the Sixth Annual Conference on Computational Learning Theory, pp 303\u2013309. Association for Computing Machinery, New York (1993)","DOI":"10.1145\/168304.168357"},{"key":"9723_CR70","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1007\/BF02414945","volume":"89","author":"JB Prolla","year":"1971","unstructured":"Prolla, J.B.: Weighted spaces of vector-valued continuous functions. Ann. Mat. Pura Appl. (4) 89, 145\u2013157 (1971)","journal-title":"Ann. Mat. Pura Appl. (4)"},{"key":"9723_CR71","volume-title":"\u00c9l\u00e9ments de math\u00e9matique. Topologie g\u00e9n\u00e9rale. Chapitres 1 \u00e0 4","author":"N Bourbaki","year":"1971","unstructured":"Bourbaki, N.: \u00c9l\u00e9ments de math\u00e9matique. Topologie g\u00e9n\u00e9rale. Chapitres 1 \u00e0 4. Hermann, Paris (1971)"},{"key":"9723_CR72","doi-asserted-by":"publisher","first-page":"444","DOI":"10.1007\/BF01898849","volume":"8","author":"RR Phelps","year":"1957","unstructured":"Phelps, R.R.: Subreflexive normed linear spaces. Arch. Math. (Basel) 8, 444\u2013450 (1957)","journal-title":"Arch. Math. (Basel)"},{"key":"9723_CR73","first-page":"61","volume":"1","author":"MI Kadec","year":"1967","unstructured":"Kadec, M.I.: A proof of the topological equivalence of all separable infinite-dimensional Banach spaces. Funkcional. Anal. i Prilo\u017een. 1, 61\u201370 (1967)","journal-title":"Funkcional. Anal. i Prilo\u017een."},{"key":"9723_CR74","doi-asserted-by":"crossref","unstructured":"Grosse-Erdmann, K.-G., Peris Manguillot, A.: Linear chaos. Universitext, Springer, London (2011)","DOI":"10.1007\/978-1-4471-2170-1"},{"key":"9723_CR75","unstructured":"P\u00e9rez Carreras, P., Bonet, J.: Barrelled locally convex spaces, North-Holland Mathematics Studies, vol. 131. North-Holland Publishing Co., Amsterdam. Notas de Matem\u00e1tica [Mathematical Notes], 113 (1987)"},{"key":"9723_CR76","unstructured":"Kreyszig, E.: Introductory functional analysis with applications, Wiley Classics Library. Wiley, New York (1989)"},{"key":"9723_CR77","volume-title":"Espaces vectoriels topologiques. Chapitres 1 \u00e0 5","author":"N Bourbaki","year":"1981","unstructured":"Bourbaki, N.: Espaces vectoriels topologiques. Chapitres 1 \u00e0 5, New. Masson, Paris (1981). \u00c9l\u00e9ments de math\u00e9matique","edition":"New"},{"issue":"3","key":"9723_CR78","doi-asserted-by":"publisher","first-page":"259","DOI":"10.4064\/sm180109-8-6","volume":"249","author":"T Kalmes","year":"2019","unstructured":"Kalmes, T.: Dynamics of weighted composition operators on function spaces defined by local properties. Studia Math. 249(3), 259\u2013301 (2019)","journal-title":"Studia Math."},{"issue":"1","key":"9723_CR79","doi-asserted-by":"publisher","first-page":"1097","DOI":"10.1016\/j.jmaa.2016.08.029","volume":"445","author":"A Przestacki","year":"2017","unstructured":"Przestacki, A.: Dynamical properties of weighted composition operators on the space of smooth functions. J. Math. Anal. Appl. 445(1), 1097\u20131113 (2017)","journal-title":"J. Math. Anal. Appl."},{"issue":"1","key":"9723_CR80","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1016\/j.jmaa.2018.04.063","volume":"465","author":"F Bayart","year":"2018","unstructured":"Bayart, F., Darji, U.B., Pires, B.: Topological transitivity and mixing of composition operators. J. Math. Anal. Appl. 465(1), 125\u2013139 (2018)","journal-title":"J. Math. Anal. Appl."},{"key":"9723_CR81","doi-asserted-by":"crossref","unstructured":"Hoffmann, H.: On the continuity of the inverses of strictly monotonic functions. Irish Math. Soc. Bull. (75), 45\u201357 (2015)","DOI":"10.33232\/BIMS.0075.45.57"},{"issue":"1","key":"9723_CR82","doi-asserted-by":"publisher","first-page":"33","DOI":"10.4064\/sm-69-1-33-40","volume":"69","author":"E Behrends","year":"1980","unstructured":"Behrends, E., Schmidt-Bichler, U.: M-structure and the Banach-Stone theorem. Studia Math. 69(1), 33\u201340 (1980\/81)","journal-title":"Studia Math."},{"key":"9723_CR83","doi-asserted-by":"crossref","unstructured":"Jarchow, H.: Locally convex spaces. B. G. Teubner, Stuttgart. Mathematische Leitf\u00e4den. [Mathematical Textbooks] (1981)","DOI":"10.1007\/978-3-322-90559-8"},{"key":"9723_CR84","doi-asserted-by":"publisher","first-page":"61","DOI":"10.5802\/aif.8","volume":"1","author":"J Dieudonn\u00e9","year":"1949","unstructured":"Dieudonn\u00e9, J., Schwartz, L.: La dualit\u00e9 dans les espaces F et LF. Ann. Inst. Fourier (Grenoble) 1, 61\u2013101 (1949)","journal-title":"Ann. Inst. Fourier (Grenoble)"}],"container-title":["Annals of Mathematics and Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10472-020-09723-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10472-020-09723-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10472-020-09723-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,28]],"date-time":"2023-01-28T14:40:25Z","timestamp":1674916825000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10472-020-09723-1"}},"subtitle":["Characterization, Construction, Representation, and Existence"],"short-title":[],"issued":{"date-parts":[[2021,1,22]]},"references-count":84,"journal-issue":{"issue":"5-6","published-print":{"date-parts":[[2021,6]]}},"alternative-id":["9723"],"URL":"https:\/\/doi.org\/10.1007\/s10472-020-09723-1","relation":{},"ISSN":["1012-2443","1573-7470"],"issn-type":[{"value":"1012-2443","type":"print"},{"value":"1573-7470","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,1,22]]},"assertion":[{"value":"27 November 2020","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 January 2021","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}