BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Department of Electrical and Computer Engineering - ECPv6.17.0//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Department of Electrical and Computer Engineering
X-ORIGINAL-URL:https://engineering.jhu.edu/ece
X-WR-CALDESC:Events for Department of Electrical and Computer Engineering
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20180311T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20181104T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20190310T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20191103T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20200308T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20201101T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20191220T100000
DTEND;TZID=America/New_York:20191220T120000
DTSTAMP:20210628T204255Z
CREATED:20210628T204255Z
LAST-MODIFIED:20210628T204255Z
UID:554055-1576836000-1576843200@engineering.jhu.edu
SUMMARY:Dissertation Defense: Akshay Rangamani
DESCRIPTION:Title: Loss Landscapes of Neural Networks and their Generalization: Theory and ApplicationsAbstract: In the last decade or so\, deep learning has revolutionized entire domains of machine learning. Neural networks have helped achieve significant improvements in computer vision\, machine translation\, speech recognition\, etc. These powerful empirical demonstrations leave a wide gap between our current theoretical understanding of neural networks and their practical performance. The theoretical questions in deep learning can be put under three broad but inter-related themes: 1) Architecture/Representation\, 2) Optimization\, and 3) Generalization. In this dissertation\, we study the landscapes of different deep learning problems to answer questions in the above themes.First\, in order to understand what representations can be learned by neural networks\, we study simple Autoencoder networks with one hidden layer of rectified linear units. We connect autoencoders to the well-known problem in signal processing of Sparse Coding. We show that the squared reconstruction error loss function has a critical point at the ground truth dictionary under an appropriate generative model.Next\, we turn our attention to a problem at the intersection of optimization and generalization. Training deep networks through empirical risk minimization is a non-convex problem with many local minima in the loss landscape. A number of empirical studies have observed that “flat minima” for neural networks tend to generalize better than sharper minima. However\, quantifying the flatness or sharpness of minima has been an issue due to possible rescaling in neural networks with positively homogenous activations. We use ideas from Riemannian geometry to define a new measure of flatness that is invariant to rescaling. We test the hypothesis that flatter minima generalize better through a number of different experiments on deep networks.Finally\, we apply deep networks to computer vision problems with compressed measurements of natural images and videos. We conduct experiments to characterize the situations in which these networks fail\, and those in which they succeed. We train deep networks to perform object detection and classification directly on these compressive measurements of images\, without trying to reconstruct the scene first. These experiments are conducted on public datasets as well as datasets specific to a sponsor of our research.
URL:https://engineering.jhu.edu/ece/event/dissertation-defense-akshay-rangamani/
LOCATION:Hackerman Hall 320\, 3101 Wyman Park Dr.\, Baltimore\, MD\, 21218\, United States
END:VEVENT
END:VCALENDAR