{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T18:36:30Z","timestamp":1770921390787,"version":"3.50.1"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032178008","type":"print"},{"value":"9783032178015","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-17801-5_29","type":"book-chapter","created":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T17:53:01Z","timestamp":1770918781000},"page":"390-403","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Reverse Mathematics for\u00a0Neural Networks"],"prefix":"10.1007","author":[{"given":"Yoshihiro","family":"Maruyama","sequence":"first","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,2,13]]},"reference":[{"issue":"6","key":"29_CR1","doi-asserted-by":"publisher","first-page":"623","DOI":"10.1016\/j.apal.2011.10.006","volume":"163","author":"V Brattka","year":"2012","unstructured":"Brattka, V., Gherardi, G., Marcone, A.: The Bolzano-Weierstrass theorem is the jump of weak K\u00f6nig\u2019s lemma. Ann. Pure Appl. Log. 163(6), 623\u2013655 (2012)","journal-title":"Ann. Pure Appl. Log."},{"issue":"4","key":"29_CR2","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."},{"key":"29_CR3","unstructured":"Eastaugh, B.: Reverse mathematics. In: Zalta, E.N., Nodelman, U. (eds.) SEP. Stanford University (2024)"},{"issue":"3","key":"29_CR4","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1016\/0893-6080(89)90003-8","volume":"2","author":"K Funahashi","year":"1989","unstructured":"Funahashi, K.: On the approximate realization of continuous mappings by neural networks. Neural Netw. 2(3), 183\u2013192 (1989)","journal-title":"Neural Netw."},{"key":"29_CR5","unstructured":"Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press (2016)"},{"key":"29_CR6","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1162\/tacl_a_00306","volume":"8","author":"M Hahn","year":"2020","unstructured":"Hahn, M.: Theoretical limitations of self-attention in neural sequence models. Trans. Assoc. Comput. Linguist. 8, 156\u2013171 (2020)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"29_CR7","doi-asserted-by":"crossref","unstructured":"Hirschfeldt, D.R.: Slicing the Truth: On the Computable and Reverse Mathematics of Combinatorial Principles. World Scientific (2014)","DOI":"10.1142\/9208"},{"issue":"2","key":"29_CR8","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."},{"issue":"5","key":"29_CR9","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."},{"issue":"6","key":"29_CR10","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":"29_CR11","unstructured":"Lu, Z., Pu, H., Wang, F., Hu, Z., Wang, L.: The expressive power of neural networks: a view from the width. In: NeurIPS (2017)"},{"issue":"12","key":"29_CR12","doi-asserted-by":"publisher","first-page":"1486","DOI":"10.1016\/j.apal.2010.05.002","volume":"161","author":"Y Maruyama","year":"2010","unstructured":"Maruyama, Y.: Fundamental results for pointfree convex geometry. Ann. Pure Appl. Logic 161(12), 1486\u20131501 (2010)","journal-title":"Ann. Pure Appl. Logic"},{"key":"29_CR13","unstructured":"Maruyama, Y.: Reasoning about fuzzy belief and common belief: with emphasis on incomparable beliefs. In: IJCAI (2011)"},{"issue":"3","key":"29_CR14","doi-asserted-by":"publisher","first-page":"565","DOI":"10.1016\/j.jpaa.2011.07.002","volume":"216","author":"Y Maruyama","year":"2012","unstructured":"Maruyama, Y.: Natural duality, modality, and coalgebra. J. Pure Appl. Algebra 216(3), 565\u2013580 (2012)","journal-title":"J. Pure Appl. Algebra"},{"key":"29_CR15","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1007\/978-3-319-22686-6_6","volume":"43","author":"Y Maruyama","year":"2016","unstructured":"Maruyama, Y.: Categorical harmony and paradoxes in proof-theoretic semantics. Adv. Proof-Theor. Semant. 43, 95\u2013114 (2016)","journal-title":"Adv. Proof-Theor. Semant."},{"key":"29_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1007\/978-3-030-67220-1_11","volume-title":"Software Engineering and Formal Methods. SEFM 2020 Collocated Workshops","author":"Y Maruyama","year":"2021","unstructured":"Maruyama, Y.: Symbolic and statistical theories of cognition: towards integrated artificial intelligence. In: Cleophas, L., Massink, M. (eds.) SEFM 2020. LNCS, vol. 12524, pp. 129\u2013146. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-67220-1_11"},{"key":"29_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1007\/978-3-032-15621-1_8","volume-title":"Applied Algorithms","author":"Y Maruyama","year":"2026","unstructured":"Maruyama, Y.: Algorithm for interpretable graph features via motivic persistent Cohomology. In: Zaroliagis, C., Bhandari, D., Gupta, P., Das, S. (eds.) ICAA 2026. LNCS, vol. 16423, pp. 87\u201399. Springer, Cham (2026). https:\/\/doi.org\/10.1007\/978-3-032-15621-1_8"},{"key":"29_CR18","unstructured":"Maruyama, Y.: Algorithms and complexity results for K-theoretic persistent homology. LNCS. Springer, Cham (2026)"},{"key":"29_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1007\/978-3-032-15621-1_7","volume-title":"Applied Algorithms","author":"Y Maruyama","year":"2026","unstructured":"Maruyama, Y.: Top-K exterior power persistent homology: algorithm, structure, and stability. In: Zaroliagis, C., Bhandari, D., Gupta, P., Das, S. (eds.) ICAA 2026. LNCS, vol. 16423, pp. 74\u201386. Springer, Cham (2026). https:\/\/doi.org\/10.1007\/978-3-032-15621-1_7"},{"key":"29_CR20","unstructured":"Maruyama, Y., Yasuda, A.: Homological representation learning for molecular graphs. In: Proceedings of Machine Learning Research (2025)"},{"key":"29_CR21","unstructured":"Maruyama, Y., Yasuda, A.: K-theoretic persistent Cohomology. In: Proceedings of Machine Learning Research (2025)"},{"key":"29_CR22","unstructured":"Maruyama, Y.: Categorical Equivariant deep learning: category-equivariant neural networks and universal approximation theorems. arXiv:2511.18417 (2025)"},{"key":"29_CR23","unstructured":"Maruyama, Y.: Learning with category-equivariant architectures for human activity recognition. arXiv:2511.01139 (2025)"},{"key":"29_CR24","unstructured":"Maruyama, Y.: Learning with category-equivariant representations for human activity recognition. arXiv:2511.00900 (2025)"},{"key":"29_CR25","unstructured":"Mont\u00fafar, G.F., Pascanu, R., Cho, K., Bengio, Y.: On the number of linear regions of deep neural networks. In: NeurIPS (2014)"},{"key":"29_CR26","first-page":"1","volume":"20","author":"M Unser","year":"2019","unstructured":"Unser, M.: A representer theorem for deep neural networks. J. Mach. Learn. Res. 20, 1\u201330 (2019)","journal-title":"J. Mach. Learn. Res."},{"key":"29_CR27","doi-asserted-by":"publisher","first-page":"296","DOI":"10.1016\/j.neunet.2018.08.019","volume":"108","author":"P Petersen","year":"2018","unstructured":"Petersen, P., Voigtlaender, F.: Optimal approximation of piecewise smooth functions using deep ReLU neural networks. Neural Netw. 108, 296\u2013330 (2018)","journal-title":"Neural Netw."},{"key":"29_CR28","unstructured":"Von Oswald, J., et al.: Transformers learn in-context by gradient descent. arXiv:2212.07677 (2022)"},{"key":"29_CR29","doi-asserted-by":"crossref","unstructured":"Simpson, S.G.: Subsystems of Second Order Arithmetic. CUP (2009)","DOI":"10.1017\/CBO9780511581007"},{"key":"29_CR30","unstructured":"Telgarsky, M.: Benefits of depth in neural networks. In: COLT (2016)"},{"key":"29_CR31","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)"},{"key":"29_CR32","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1016\/j.neunet.2017.07.002","volume":"94","author":"D Yarotsky","year":"2017","unstructured":"Yarotsky, D.: Error bounds for approximations with deep ReLU networks. Neural Netw. 94, 103\u2013114 (2017)","journal-title":"Neural Netw."},{"key":"29_CR33","unstructured":"Yun, C., Bhojanapalli, S., Rawat, A., Reddi, S., Kumar, S.: Are transformers universal approximators of sequence-to-sequence functions? In: ICLR (2020)"}],"container-title":["Lecture Notes in Computer Science","SOFSEM 2026: Theory and Practice of Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-17801-5_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T17:53:06Z","timestamp":1770918786000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-17801-5_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032178008","9783032178015"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-17801-5_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"13 February 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SOFSEM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Current Trends in Theory and Practice of Computer Science","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Krakow","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Poland","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 February 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 February 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"51","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"sofsem2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/sofsem.uj.edu.pl\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}