BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//White City Innovation District - ECPv6.15.20//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:White City Innovation District
X-ORIGINAL-URL:https://www.whitecityinnovationdistrict.org.uk
X-WR-CALDESC:Events for White City Innovation District
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:20240331T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
TZNAME:GMT
DTSTART:20241027T010000
END:STANDARD
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
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Europe/London:20250605T130000
DTEND;TZID=Europe/London:20250605T140000
DTSTAMP:20260421T224342
CREATED:20250522T130134Z
LAST-MODIFIED:20250522T130134Z
UID:3568-1749128400-1749132000@www.whitecityinnovationdistrict.org.uk
SUMMARY:I-X Seminar: Logically-Consistent Deep Learning
DESCRIPTION:Join I-X for the next event in its popular seminar series. Dr Antonio Vergari (University of Edinburgh) will be delivering a talk entitled “Logically-Consistent Deep Learning”. \nHybrid location:  I-X LRT608A level 6 (I-HUB) & via Teams \nSeminar Summary \nGuaranteeing the safety and reliability of deep learning models is of crucial importance\, especially in many high-stake application scenarios. In this lecture\, I will focus on the key challenge of designing probabilistic deep learning models that are reliable and yet efficient by design. I will do so within the framework of probabilistic circuits: overparametrized and computational graphs that are just neural networks with lots of structure\, enough to guarantee the tractable computation of the probabilistic reasoning scenarios of interest\, while not compromising their expressiveness. Second\, I will discuss how we can use circuits to build a reliable foundation for neuro-symbolic AI. That is\, for example\, to provably satisfy certain constraints we can express in propositional logic in neural networks as to increase their performance and robustness. These models can be thought of being “verified by design” and I will showcase some recent applications of this constraint satisfaction by design e.g.\, scaling link prediction in graphs with millions of nodes and when constraints are both on continuous and discrete domains.
URL:https://www.whitecityinnovationdistrict.org.uk/event/i-x-seminar-logically-consistent-deep-learning/
LOCATION:I-HUB\, Imperial White City Campus\, 84 Wood Lane\, London\, W12 0BZ\, United Kingdom
ATTACH;FMTTYPE=image/png:https://www.whitecityinnovationdistrict.org.uk/wp-content/uploads/sites/10/2025/05/I-X-Seminar-Series_May-2025.png
END:VEVENT
END:VCALENDAR