BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//TRIANGEL Transfer | Kultur | Raum - ECPv6.16.1//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:TRIANGEL Transfer | Kultur | Raum
X-ORIGINAL-URL:https://www.triangel.space
X-WR-CALDESC:Veranstaltungen für TRIANGEL Transfer | Kultur | Raum
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:Europe/Berlin
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20220327T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20221030T010000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20230326T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20231029T010000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20240331T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20241027T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Europe/Berlin:20231005T100000
DTEND;TZID=Europe/Berlin:20231006T180000
DTSTAMP:20261002T003738
CREATED:20230921T104057Z
LAST-MODIFIED:20231004T101151Z
UID:8513-1696500000-1696615200@www.triangel.space
SUMMARY:Deep Learning - Recent Advances in Kernel Methods for Neural Networks
DESCRIPTION:©  Karlsruher Institut für Technologie\n\n\n\n\n\n\n\nSparked by the success of deep neural networks in many practical applications\, there has been an increasing interest in analyzing these methods from a statistical perspective. In recent years\, advances in the theory of neural networks and kernels have brought both fields closer together. \n\n\n\nThis not only sparked new interest and with that fresh ideas in the field of kernels\, it also enabled research to explain phenomena occurring in neural networks. Double descent [Belkin et al.\, 2018]\, the usefulness of overparametrization (for example in Autoencoder architectures) [Radhakrishnan et al.\, 2018] or the Neural Tangent Kernel [Jacot et al.\, 2018] are among those. Notably\, Radhakrishnan and co-authors [Radhakrishnan et al.\, 2022] showed that neural networks merely learn something called the ‘Expected Gradient Outer Product’ (EGOP). They showed that using the EGOP within a simple kernel framework outperforms not only neural networks but also methods such as Gradient Boosting and Random Forests in most cases. \n\n\n\nIn this workshop Adit Radhakrishnan will teach the mathematical reasoning behind the above-mentioned methods\, but also how they are applied in practical applications (mainly from biology). In interactive Python coding sessions\, participants will have the chance to develop these methods themselves. The overarching goal of the workshop therefore is to learn about a mathematically founded way of applying deep learning in practice and to disentangle myth and actual capabilities of deep learning and kernels. The power of these methods is that they make use of mechanisms in neural networks without the overhead of training them. These methods are hence applicable to many practical problems\, with or without a plethora of available data. \n\n\n\nMore information can be found here. \n\n\n\nAbout Adit RadhakrishnanAdit is a George F. Carrier postdoctoral fellow at Harvard. He completed his Ph.D. in electrical engineering and computer science (EECS) at MIT advised by Caroline Uhler and was a Ph.D. fellow at the Eric and Wendy Schmidt Center at the Broad Institute of MIT and Harvard. He received his M.Eng. in EECS and his Bachelor’s of Science in Math and EECS from MIT. His research focuses on advancing theoretical foundations of machine learning in order to develop new methods for tackling biomedical problems. In his talk at KIT\, he will present some of his recent projects\, which shed light on some of the mysteries of deep learning that are of interest to both theorists and practitioners. \n\n\n\nAdit Radhakrishnan\n\n\n\n\n\n \n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n \n\n\n\nVeranstalter\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nVeranstaltungsort
URL:https://www.triangel.space/event/deep-learning-recent-advances-in-kernel-methods-for-neural-networks/
LOCATION:TRIANGEL Transfer | Kultur | Raum\, Kaiserstraße 93\, Karlsruhe\, 76133
CATEGORIES:Informationsveranstaltung,Networking,Workshop
ATTACH;FMTTYPE=image/jpeg:https://www.triangel.space/wp-content/uploads/2023/09/20221212-SG-01-068-scaled.jpg
ORGANIZER;CN="TRIANGEL Transfer | Kultur | Raum":MAILTO:hello@triangel.space
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Europe/Berlin:20231009T103000
DTEND;TZID=Europe/Berlin:20231009T130000
DTSTAMP:20261002T003738
CREATED:20230629T083658Z
LAST-MODIFIED:20230629T083658Z
UID:7828-1696847400-1696856400@www.triangel.space
SUMMARY:CyberSec Get-Together
DESCRIPTION:Bild: © KIT\n\n\n\n\n\nDas Thema Cybersicherheit ist zurzeit in aller Munde. Du willst mehr über aktuelle Forschung erfahren und dich mit der Security Community am KIT vernetzen? Dann schau beim CyberSec Get-Together vorbei! \n\n\n\nUm den großen gesellschaftlichen Herausforderungen gerecht zu werden\, arbeiten dutzende Forschende am KIT intensiv an Cybersicherheitslösungen für heute und morgen. Mit dem Ziel aktuelle Forschung zu diskutieren und den Austausch zwischen Wissenschaft\, Gesellschaft und Wirtschaft zu fördern\, veranstaltet die KIT Graduate School Cyber Security einmal monatlich das CyberSec Get-Together. \n\n\n\nProgramm\n\n\n\n\n\n10:30 – 11:30 UhrReading RoundtableTeilnehmende beim Reading Roundtable diskutieren unter Leitung unseres Kommunikationsexperten über wegweisende Papiere der Cybersicherheitsforschung.11:30 – 12:00 UhrCyberSec SeminarIm Rahmen des CyberSec Seminars stellen Promovierende aktuelle Forschungssergebnisse vor und stellen diese zur Diskussion.12:00 – 13:00 UhrSecurity & Privacy LunchDer abschließende Security & Privacy Lunch soll die Möglichkeit zum weiteren Austausch und zur Vernetzung in lockerer Atmosphäre bieten.\n\n\n\n\n\nDas Event ist kostenlos und richtet sich an alle Interessierten aus Forschung\, Wirtschaft/Industrie und technikinteressierter Öffentlichkeit\, die mehr über aktuelle Fragen\, Ergebnisse und Herausforderung von Cybersicherheitsforschung erfahren wollen. \n\n\n\n \n\n\n\nCorona Hinweis\n\n\n\nCorona-Hygienevorschriften und weitere Hinweise findet ihr hier.   \n\n\n\n \n\n\n\n \n\n\n\n\n\n \n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nVeranstalter\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nVeranstaltungsort
URL:https://www.triangel.space/event/cybersec-get-together-9/
LOCATION:TRIANGEL Transfer | Kultur | Raum\, Kaiserstraße 93\, Karlsruhe\, 76133
CATEGORIES:Informationsveranstaltung,Networking,Talk
ATTACH;FMTTYPE=image/jpeg:https://www.triangel.space/wp-content/uploads/2023/01/Triangel_CyberSec_Bild-scaled.jpg
END:VEVENT
END:VCALENDAR