BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Columbia Entrepreneurship - ECPv6.15.11//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://entrepreneurship.columbia.edu
X-WR-CALDESC:Events for Columbia Entrepreneurship
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:UTC
BEGIN:STANDARD
TZOFFSETFROM:+0000
TZOFFSETTO:+0000
TZNAME:UTC
DTSTART:20160101T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=UTC:20170922T100000
DTEND;TZID=UTC:20170922T110000
DTSTAMP:20260404T055526
CREATED:20170915T152924Z
LAST-MODIFIED:20170915T152924Z
UID:10412-1506074400-1506078000@entrepreneurship.columbia.edu
SUMMARY:Data Science Institute Colloquium Series Event: What Can Deep Learning Learn from Linear Regression
DESCRIPTION:OPEN TO ALL \nABSTRACT \nWhen training large-scale deep neural networks for pattern recognition\, hundreds of hours on clusters of GPUs are required to achieve state-of-the-art performance. Improved optimization algorithms could potentially enable faster industrial prototyping and make training contemporary models more accessible. \nIn this talk\, I will attempt to distill the key difficulties in optimizing large\, deep neural networks for pattern recognition. In particular\, I will emphasize that many of the popularized notions of what make these problems “hard” are not true impediments at all. I will show that it is not only easy to globally optimize neural networks\, but that such global optimization remains easy when fitting completely random data. \nI will argue instead that the source of difficulty in deep learning is a lack of understanding of generalization—namely understanding behavior on new and unseen data. By appealing to standard concepts from linear regression\, I will describe why certain popular theories of generalization fail to explain the success of large neural nets. I will close with some possible approaches to patching this theory and guiding the engineering of deep learning models with enormous capacity. \n 
URL:https://entrepreneurship.columbia.edu/event/data-science-institute-colloquium-series-event-can-deep-learning-learn-linear-regression/
CATEGORIES:Columbia Data Science Institute
END:VEVENT
END:VCALENDAR