BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Centre for Mathematical Sciences - ECPv5.4.0.2//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Centre for Mathematical Sciences
X-ORIGINAL-URL:https://math-sciences.org
X-WR-CALDESC:Events for Centre for Mathematical Sciences
BEGIN:VTIMEZONE
TZID:UTC
BEGIN:STANDARD
TZOFFSETFROM:+0000
TZOFFSETTO:+0000
TZNAME:UTC
DTSTART:20210101T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=UTC:20210428T160000
DTEND;TZID=UTC:20210428T170000
DTSTAMP:20230401T140033
CREATED:20210311T181700Z
LAST-MODIFIED:20210416T113415Z
UID:4024-1619625600-1619629200@math-sciences.org
SUMMARY:Dimitrios Bachtis (Swansea)
DESCRIPTION:Quantum field-theoretic machine learning \nThe precise equivalence between discretized Euclidean field theories and Markov random fields\, as established by the Hammersley-Clifford theorem\, opens up the opportunity to investigate machine learning from the perspective of quantum field theory. In this talk I will discuss a variety of interconnected topics: Markov properties for quantum fields\, the derivation of machine learning algorithms and of neural networks from the $\phi^{4}$ scalar field theory and the minimization of distance metrics between probability distributions. I will then conclude by presenting applications pertinent to the quantum field-theoretic machine learning algorithms.
URL:https://math-sciences.org/event/dimitrios-bachtis-swansea/
LOCATION:Zoom
CATEGORIES:Seminars,Theoretical Physics
END:VEVENT
END:VCALENDAR