{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T16:27:09Z","timestamp":1743006429703,"version":"3.40.3"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031477232"},{"type":"electronic","value":"9783031477249"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-47724-9_24","type":"book-chapter","created":{"date-parts":[[2024,4,18]],"date-time":"2024-04-18T20:29:08Z","timestamp":1713472148000},"page":"364-375","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Why Neural Networks Work"],"prefix":"10.1007","author":[{"given":"Sayandev","family":"Mukherjee","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bernardo A.","family":"Huberman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,4,19]]},"reference":[{"key":"24_CR1","unstructured":"Dasgupta, S., Tosh, C.: Expressivity of expand-and-sparsify representations (2020). arXiv:2006.03741"},{"key":"24_CR2","unstructured":"Frankle, J., Carbin, M.: The lottery ticket hypothesis\u2013finding sparse, trainable neural networks. In: ICLR (2019). https:\/\/openreview.net\/forum?id=rJl-b3RcF7"},{"key":"24_CR3","unstructured":"Frankle, J., Schwab, D.J., Morcos, A.S.: Training batchnorm and only batchnorm: on the expressive power of random features in CNNs (2020). arXiv.org\/abs\/2003.00152"},{"issue":"56","key":"24_CR4","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(56), 1929\u20131958 (2014)","journal-title":"J. Mach. Learn. Res."},{"key":"24_CR5","unstructured":"Zhang, C., Bengio, S., Hardt, M., Recht, B., Vinyals, O.: Understanding deep learning requires rethinking generalization. In: Proceedings of 5th International Conference on Learning Representations (ICLR 2017). https:\/\/openreview.net\/forum?id=Sy8gdB9xx"},{"issue":"3","key":"24_CR6","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1145\/3446776","volume":"64","author":"C Zhang","year":"2021","unstructured":"Zhang, C., Bengio, S., Hardt, M., Recht, B., Vinyals, O.: Understanding deep learning (still) requires rethinking generalization. Commun. ACM 64(3), 107\u2013115 (2021)","journal-title":"Commun. ACM"},{"issue":"32","key":"24_CR7","doi-asserted-by":"publisher","first-page":"15849","DOI":"10.1073\/pnas.1903070116","volume":"116","author":"M Belkin","year":"2019","unstructured":"Belkin, M., Hsu, D., Ma, S., Mandal, S.: Reconciling modern machine-learning practice and the classical bias-variance trade-off. Proc. Natl. Acad. Sci. 116(32), 15849\u201315854 (2019)","journal-title":"Proc. Natl. Acad. Sci."},{"key":"24_CR8","unstructured":"Bartlett, P.L., Foster, D.J., Telgarsky, M.J.: Spectrally-normalized margin bounds for neural networks. In: Advances in Neural Information Processing Systems 30 (NeurIPS 2017) (2017)"},{"key":"24_CR9","unstructured":"Chizat, L., Oyallon, E., Bach, F.: On lazy training in differentiable programming. In: Advances in Neural Information Processing Systems (NeurIPS 2019), vol. 32 (2019)"},{"key":"24_CR10","doi-asserted-by":"crossref","unstructured":"Roberts, D.A., Yaida, S., Hanin, B.: The Principles of Deep Learning Theory. Cambridge University Press (2022)","DOI":"10.1017\/9781009023405"},{"issue":"8","key":"24_CR11","doi-asserted-by":"publisher","first-page":"832","DOI":"10.1109\/34.709601","volume":"20","author":"TK Ho","year":"1998","unstructured":"Ho, T.K.: The random subspace method for constructing decision forests. IEEE Trans. Pattern Anal. Mach. Intell. 20(8), 832\u2013844 (1998)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"1","key":"24_CR12","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman, L.: Random forests. Mach. Learn. 45(1), 5\u201332 (2001)","journal-title":"Mach. Learn."},{"key":"24_CR13","unstructured":"Rahimi, A., Recht, B.: Random features for large-scale kernel machines. In: Advances in Neural Information Processing Systems 20 (NeurIPS 2007) (2007)"},{"issue":"1","key":"24_CR14","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1002\/rsa.10073","volume":"22","author":"S Dasgupta","year":"2003","unstructured":"Dasgupta, S., Gupta, A.: An elementary proof of a theorem of Johnson and Lindenstrauss. Random Struct. Algorithms 22(1), 60\u201365 (2003)","journal-title":"Random Struct. Algorithms"},{"key":"24_CR15","unstructured":"Wikipedia: Johnson-Lindenstrauss lemma. https:\/\/en.wikipedia.org\/wiki\/Johnson-Lindenstrauss_lemma"},{"key":"24_CR16","doi-asserted-by":"publisher","first-page":"793","DOI":"10.1126\/science.aam9868","volume":"358","author":"S Dasgupta","year":"2017","unstructured":"Dasgupta, S., Stevens, C.F., Navlakha, S.: A neural algorithm for a fundamental computing problem. Science 358, 793\u2013796 (2017)","journal-title":"Science"},{"key":"24_CR17","unstructured":"Papadimitriou, C.H., Vempala, S.S.: Random projection in the brain and computation with assemblies of neurons. In: 10th Innovations in Theoretical Computer Science (ITCS 2019), vol. 57, pp. 1\u201319 (2019)"},{"issue":"51","key":"24_CR18","doi-asserted-by":"publisher","first-page":"13093","DOI":"10.1073\/pnas.1814448115","volume":"115","author":"S Dasgupta","year":"2018","unstructured":"Dasgupta, S., Sheehan, T.C., Stevens, C.F., Navlakha, S.: A neural data structure for novelty detection. Proc. Natl. Acad. Sci. 115(51), 13093\u201313098 (2018)","journal-title":"Proc. Natl. Acad. Sci."},{"issue":"3","key":"24_CR19","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1016\/0893-9659(93)90023-G","volume":"6","author":"PC Kainen","year":"1993","unstructured":"Kainen, P.C., Kurkov\u00e1, V.: Quasiorthogonal dimension of Euclidean spaces. Appl. Math. Lett. 6(3), 7\u201310 (1993)","journal-title":"Appl. Math. Lett."},{"key":"24_CR20","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1016\/j.ins.2015.09.021","volume":"364\u2013365","author":"AN Gorban","year":"2016","unstructured":"Gorban, A.N., Tyukin, I.Y., Prokhorov, D.V., Sofeikov, K.I.: Approximation with random bases: Pro et Contra. Inf. Sci. 364\u2013365, 129\u2013145 (2016)","journal-title":"Inf. Sci."},{"key":"24_CR21","unstructured":"Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, published in Proceedings of Machine Learning Research, vol. 9, pp. 249\u2013256 (2010)"},{"key":"24_CR22","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: ICCV, pp. 1026\u20131034 (2015)","DOI":"10.1109\/ICCV.2015.123"},{"key":"24_CR23","unstructured":"LeCun, Y., Cortes, C., Burges, C.J.C.: The MNIST database of handwritten digits. http:\/\/yann.lecun.com\/exdb\/mnist\/"},{"key":"24_CR24","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1017\/S0962492921000027","volume":"30","author":"P Bartlett","year":"2021","unstructured":"Bartlett, P., Montanari, A., Rakhlin, A.: Deep learning: a statistical viewpoint. Acta Numer 30, 87\u2013201 (2021)","journal-title":"Acta Numer"},{"key":"24_CR25","doi-asserted-by":"crossref","unstructured":"Hara, K., Saitoh, D., Shouno, H.: Analysis of dropout learning regarded as ensemble learning. In: Proceedings of 25th International Conference Artificial Neural Networks (ICANN 2016)","DOI":"10.1007\/978-3-319-44781-0_9"},{"key":"24_CR26","unstructured":"Burkholz, R., Laha, N., Mukherjee, R., Gotovos, A.: On the existence of universal lottery tickets. In: Proceedings of 10th International Conference on Learning Representations (ICLR 2022). http:\/\/openreview.net\/forum?id=SYB4WrJql1n"},{"key":"24_CR27","unstructured":"Burkholz, R.: Convolutional and residual networks provably contain lottery tickets. In: ICML 2022. Proceedings of Machine Learning Research, vol. 162, pp. 2414\u20132433 (2022)"}],"container-title":["Lecture Notes in Networks and Systems","Intelligent Systems and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-47724-9_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,18]],"date-time":"2024-04-18T20:37:36Z","timestamp":1713472656000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-47724-9_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031477232","9783031477249"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-47724-9_24","relation":{},"ISSN":["2367-3370","2367-3389"],"issn-type":[{"type":"print","value":"2367-3370"},{"type":"electronic","value":"2367-3389"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"19 April 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}