BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//SECURITY & APPLIED LOGIC - ECPv6.15.9//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:SECURITY & APPLIED LOGIC
X-ORIGINAL-URL:https://sal.cs.unibuc.ro
X-WR-CALDESC:Events for SECURITY & APPLIED LOGIC
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:Europe/Bucharest
BEGIN:DAYLIGHT
TZOFFSETFROM:+0200
TZOFFSETTO:+0300
TZNAME:EEST
DTSTART:20170326T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0300
TZOFFSETTO:+0200
TZNAME:EET
DTSTART:20171029T010000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:+0200
TZOFFSETTO:+0300
TZNAME:EEST
DTSTART:20180325T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0300
TZOFFSETTO:+0200
TZNAME:EET
DTSTART:20181028T010000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:+0200
TZOFFSETTO:+0300
TZNAME:EEST
DTSTART:20190331T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0300
TZOFFSETTO:+0200
TZNAME:EET
DTSTART:20191027T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Europe/Bucharest:20181129T083000
DTEND;TZID=Europe/Bucharest:20181129T103000
DTSTAMP:20260403T204826
CREATED:20181126T105140Z
LAST-MODIFIED:20181126T111443Z
UID:200-1543480200-1543487400@sal.cs.unibuc.ro
SUMMARY:Machine Learning Framework for Security Applications
DESCRIPTION:Speaker: Paul Irofti (University of Bucharest). \n\nMachine learning helps us tackle large and apparently intractable optimization problems. Even though neural networks are by far the most popular choice in the field\, we focus on dictionary learning (DL) for sparse representations (SR) instead. Our preference is motivated by the much simpler model that provides faster methods with a solid theoretical background\, understanding and interpretability. \nIn fact it has been recently shown that the forward pass inside neural networks is equivalent to performing sparse representation. Thus performing dictionary learning can be interpreted as a backward pass on a much simpler and smaller model. This relaxation comes with a small performance hit in exchange for the large reduction in algorithm complexity. \nOur talk will focus on adapting DL to Big Data conditions\, DL classification and the problem of malware identification\,  nomaly detection\, online DL and Internet of Things applications.
URL:https://sal.cs.unibuc.ro/event/machine-learning-framework-for-security-applications/
LOCATION:Facultatea de Matematica si Informatica\, sala 202
CATEGORIES:Security Seminar,Seminar
END:VEVENT
END:VCALENDAR