BEGIN:VCALENDAR
VERSION:2.0
METHOD:PUBLISH
CALSCALE:GREGORIAN
PRODID:-//WordPress - MECv6.5.6//EN
X-ORIGINAL-URL:https://cmc.deusto.eus/
X-WR-CALNAME:cmc.deusto.eus
X-WR-CALDESC:DeustoCCM - Chair of Computational Mathematics at University of Deusto
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-PUBLISHED-TTL:PT1H
X-MS-OLK-FORCEINSPECTOROPEN:TRUE
BEGIN:VEVENT
CLASS:PUBLIC
UID:MEC-d68064201291ce47be8ac5d3918bcb49@cmc.deusto.eus
DTSTART:20250701T103000Z
DTEND:20250701T113000Z
DTSTAMP:20250609T110200Z
CREATED:20250609
LAST-MODIFIED:20250611
PRIORITY:5
TRANSP:OPAQUE
SUMMARY:DeustoCCM Seminar: Universal approximation and convexified training in neural networks
DESCRIPTION:Date: Tue. July 1, 2025 (12:30H)\nEvent: DeustoCCM Seminar\nTitle: Universal approximation and convexified training in neural networks\nSpeaker: Prof. Dr. Kang Liu\nAffiliation: Université Bourgogne Europe\nAbstract. The universal approximation property (UAP) of neural networks (NNs) provides a theoretical foundation for the modern era of artificial intelligence. In this presentation, we revisit several key UAP results for NNs and extend them to dynamical systems through the framework of semi-autonomous neural ordinary differential equations (SA-NODEs). Although the approximation error can be made arbitrarily small, training NNs involves solving high-dimensional, non-convex optimization problems. By leveraging mean-field techniques, we convexify the training process, offering valuable insights into practical aspects such as generalization bounds, hyperparameter selection, and scaling laws.\nWHERE\nUniversity of Deusto, DeustoTech.\nRoom: Logistar\nUnibertsitate Etorb., 24, 48007 Bilbao, Bizkaia\n
URL:https://cmc.deusto.eus/events-calendar/deustoccm-seminar-01jul2025/
ORGANIZER;CN=DeustoCCM - Chair of Computational Mathematics:MAILTO:
CATEGORIES:Events Calendar,Events Calendar Past
LOCATION:Unibertsitate Etorb., 24, 48007 Bilbao, Bizkaia
ATTACH;FMTTYPE=image/png:https://cmc.deusto.eus/wp-content/uploads/DeustoCCMseminar_kLiu_01jul2025.png
END:VEVENT
END:VCALENDAR