BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Erlangen AI Hub - ECPv6.18.2//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://erlangenhub.ox.ac.uk
X-WR-CALDESC:Events for Erlangen AI Hub
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:Europe/London
BEGIN:DAYLIGHT
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
TZNAME:BST
DTSTART:20250330T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
TZNAME:GMT
DTSTART:20251026T010000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
TZNAME:BST
DTSTART:20260329T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
TZNAME:GMT
DTSTART:20261025T010000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
TZNAME:BST
DTSTART:20270328T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
TZNAME:GMT
DTSTART:20271031T010000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
TZNAME:BST
DTSTART:20280326T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
TZNAME:GMT
DTSTART:20281029T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Europe/London:20261117T130000
DTEND;TZID=Europe/London:20261117T140000
DTSTAMP:20261023T160550Z
CREATED:20261023T160127Z
LAST-MODIFIED:20261023T160550Z
UID:1345-1794920400-1794924000@erlangenhub.ox.ac.uk
SUMMARY:Singular Learning Theory: A Mathematical Introduction
DESCRIPTION:Speaker: Kamillo Ferry\, Imperial College London \nTitle: Singular Learning Theory: A Mathematical Introduction \nAbstract: Classical statistics rests on an assumption that modern machine learning almost never satisfies: that a model’s parameters can be identified from data\, so that near the truth the model looks locally like a Euclidean space of known dimension. In neural networks\, mixture models and matrix factorisations\, many different parameters describe the same model. The set of optimal parameters is then a singular real algebraic variety\, and familiar tools such as the Fisher information and the BIC break down. Watanabe’s singular learning theory shows that the asymptotics of Bayesian learning are nevertheless governed by a single invariant of this singularity\, the real log canonical threshold\, which can be read off from a resolution of singularities. This talk is an introduction to the mathematics of the theory: why algebraic geometry enters\, how resolution of singularities turns an analytic question into a combinatorial one\, and what can be computed exactly. I will work through examples\, from toy models to reduced-rank regression. No background in algebraic geometry is assumed. \nJoin: https://teams.microsoft.com/meet/3395756456794587?p=KXola0KUUnCaaSx1QX \nWe ask that you please familiarise yourself with the Hub’s code of conduct prior to attendance. Please note\, this talk will be recorded.
URL:https://erlangenhub.ox.ac.uk/event/singular-learning-theory-a-mathematical-introduction/
ATTACH;FMTTYPE=image/png:https://erlangenhub.ox.ac.uk/wp-content/uploads/2026/10/Hub-seminar-series-templates-4.png
END:VEVENT
BEGIN:VEVENT
DTSTART;VALUE=DATE:20261124
DTEND;VALUE=DATE:20261126
DTSTAMP:20261023T130506Z
CREATED:20260930T165103Z
LAST-MODIFIED:20261023T130506Z
UID:1210-1795478400-1795651199@erlangenhub.ox.ac.uk
SUMMARY:UK AI Research Symposium
DESCRIPTION:The UK AI Research Symposium (UKAIRS) is the premier national gathering for the UK artificial intelligence research community. Organized in collaboration with UKRI\, RAI UK\, the national AI Hubs\, and CDT centres\, UKAIRS purpose is to bring together researchers and stakeholders from across disciplines\, including computer science\, engineering\, humanities\, and healthcare\, to showcase leading research\, encourage collaboration\, identify cross-fertilisation opportunities\, and help shape the future direction of AI research in the UK. Find out more and register here.
URL:https://erlangenhub.ox.ac.uk/event/uk-ai-research-symposium/
LOCATION:John McIntyre Conference Centre\, Pollock Estate\, Edinburgh\, John McIntyre Conference Centre on Pollock Estate\, Edinburgh\, EH16 5AY\, United Kingdom
ATTACH;FMTTYPE=image/jpeg:https://erlangenhub.ox.ac.uk/wp-content/uploads/2026/09/0_UKAIRS_2026_BANNER_new_2-1.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Europe/London:20270316T100000
DTEND;TZID=Europe/London:20270316T170000
DTSTAMP:20261023T133309Z
CREATED:20261023T130239Z
LAST-MODIFIED:20261023T133309Z
UID:1333-1805191200-1805216400@erlangenhub.ox.ac.uk
SUMMARY:Foundations of AI First Rodeo
DESCRIPTION:The Erlangen AI Hub will host a one-day event at the Mathematical Institute\, University of Oxford\, bringing together PhD students and ECRs from the mathematical and computational sciences across UK HEIs. \nThe event will invite participants to look beyond their immediate research areas and engage with the broader landscape in which AI research and innovation are developing. Drawing on perspectives from academia\, industry\, government and the public sector\, the programme will explore how AI is reshaping research\, where emerging technological capabilities may lead\, how approaches to regulation and responsible innovation are evolving\, and what these developments mean for the next generation of researchers. \nFurther details and a link to register will be announced shortly.
URL:https://erlangenhub.ox.ac.uk/event/foundations-of-ai-first-rodeo/
LOCATION:Mathematical Institute\, University of Oxford
ATTACH;FMTTYPE=image/png:https://erlangenhub.ox.ac.uk/wp-content/uploads/2026/10/Durham-Conference-2027-Mathematics-Forum-.png
END:VEVENT
BEGIN:VEVENT
DTSTART;VALUE=DATE:20270921
DTEND;VALUE=DATE:20270924
DTSTAMP:20261023T125352Z
CREATED:20261001T083612Z
LAST-MODIFIED:20261023T125352Z
UID:1216-1821484800-1821743999@erlangenhub.ox.ac.uk
SUMMARY:Mathematical Foundations of AI Conference 2027
DESCRIPTION:Our third annual Mathematical Foundations of AI Conference will be held at Durham University from 21st-23rd September 2027. Further details will be announced shortly.
URL:https://erlangenhub.ox.ac.uk/event/mathematical-foundations-of-ai-conference-2027/
LOCATION:Durham University\, Durham\, DH1 3LE
ATTACH;FMTTYPE=image/png:https://erlangenhub.ox.ac.uk/wp-content/uploads/2026/10/Durham-Conference-2027-_-Mathematics-Forum-.png
END:VEVENT
END:VCALENDAR