{"id":1233,"date":"2024-06-11T14:01:49","date_gmt":"2024-06-11T12:01:49","guid":{"rendered":"https:\/\/www.unioviedo.es\/fgs2024\/?page_id=1233"},"modified":"2024-06-11T14:01:49","modified_gmt":"2024-06-11T12:01:49","slug":"ms10-optimal-control-and-machine-learning-recent-advances","status":"publish","type":"page","link":"https:\/\/www.unioviedo.es\/fgs2024\/index.php\/scientific-program\/ms10-optimal-control-and-machine-learning-recent-advances\/","title":{"rendered":"MS10: Optimal control and machine learning: recent advances"},"content":{"rendered":"\nOver the last decade, machine learning techniques have been widely used in a variety\nof applications. They have demonstrated their remarkable capabilities to extract patterns and make\npredictions from large datasets. New approaches based on these techniques have notably been developed\nin the context of optimal control, in order to offer better alternatives to the study of certain\nproblems deemed to be complex. On the other hand, although machine learning algorithms are producing\nextraordinary results, they still require a solid mathematical theory that can be used to analyze\nand build generic neural networks adapted to each type of problem. Recent work has enabled neural\nnetworks to be described as discretized forms of optimal control problems, so that certain essential\nproperties can be analyzed through optimal control theory. The aim of this mini-symposium is then to\npresent, on the one hand, some recent applications of machine learning techniques in optimal control\ncontext and, on the other hand, how optimal control theory can help to build and analyze neural\nnetworks.\n\nMore precisely, Mario Sperl (University of Bayreuth) will present how deep neural networks can be\nemployed for a curse-of-dimensionality free approximation of optimal value function. Sergio Rodrigues\n(Johann Radon Institute for Computational and Applied Mathematics) will introduced an approach\nbased on neural networks for the computation of an optimal feedback control minimizing the quadratic\nenergy cost for semilinear parabolic equations. Olivier Bokanowski (Universit\u00b4e Paris Cit\u00b4e) will propose\nnew neural network approximations of the differential games strategies in feedback form, for which he\nwill provide error estimates. Finally, Antonio Alvarez Lopez (Universidad Aut\u00b4onoma de Madrid) will\nshow how optimal control theory can be used to estimate the number of neurons required for efficient\nclassification.<br>\n\n<strong>Mini symposium organizers:<\/strong><br>\nSofya Maslovskaya (Universit\u00e4t Paderborn)<br>\nBoris Wembe (Universit\u00e4t Paderborn)<br>\n<\/p>\n<p>\n<strong>Session 6. Room A5, Friday 09:00-11:00.<\/strong><br>\n <strong>Chair:<\/strong> Sofya Maslovskaya (Universit\u00e4t Paderborn)<\/strong><br>\n<strong>Speakers:<\/strong><br>\nMario Sperl (University of Bayreuth) <em>Neural network-based approximation of optimal value functions: exploring decaying sensitivity<\/em><br>\nOlivier Bokanowski (Universit\u00e9 Paris Cit\u00e9) <em>Neural network for differential games<\/em><br>\nSergio S. Rodrigues (Johann Radon Institute for Computational and Applied Mathematics (RICAM) of the Austrian Academy of Sciences) <em>Stabilization of semilinear parabolic equations: explicit and optimal control based feedbacks.<\/em><br>\nAntonio \u00c1lvarez L\u00f3pez (Universidad Aut\u00f3noma de Madrid) <em>Controllability of neural ODEs for data classification.<\/em><br>\n<\/p>\n\n","protected":false},"excerpt":{"rendered":"<p>Over the last decade, machine learning techniques have been widely used in a variety of applications. They have demonstrated their&hellip; <\/p>\n","protected":false},"author":3,"featured_media":0,"parent":618,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-1233","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/www.unioviedo.es\/fgs2024\/index.php\/wp-json\/wp\/v2\/pages\/1233","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.unioviedo.es\/fgs2024\/index.php\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/www.unioviedo.es\/fgs2024\/index.php\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/www.unioviedo.es\/fgs2024\/index.php\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/www.unioviedo.es\/fgs2024\/index.php\/wp-json\/wp\/v2\/comments?post=1233"}],"version-history":[{"count":1,"href":"https:\/\/www.unioviedo.es\/fgs2024\/index.php\/wp-json\/wp\/v2\/pages\/1233\/revisions"}],"predecessor-version":[{"id":1234,"href":"https:\/\/www.unioviedo.es\/fgs2024\/index.php\/wp-json\/wp\/v2\/pages\/1233\/revisions\/1234"}],"up":[{"embeddable":true,"href":"https:\/\/www.unioviedo.es\/fgs2024\/index.php\/wp-json\/wp\/v2\/pages\/618"}],"wp:attachment":[{"href":"https:\/\/www.unioviedo.es\/fgs2024\/index.php\/wp-json\/wp\/v2\/media?parent=1233"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}