Photos and videos are now a main mode of communication, used to tell stories, share experiences and convey ideas. However, common media editing tools are often either too complex to master, or oversimplified and limited.
Computer vision has advanced in leaps and bounds over the past few years, owing largely to the re-popularization of convolutional neural networks. Multiple claims are being heard that machine vision is maturing and will (or already has) surpassed human capabilities. This is far from the truth -- we are only beginning to scratch the surface of truly interesting problems. Very large gaps still exist between human and machine vision - in how they learn and in how well they perform.
Growing complexity of network operations is the subject of many debates. In general, there are two major factors impacting complexity of network operations: the size and structure of a manageable state and frequency of its changes. Networks should be autonomous as possible, ideally, completely excluding operators from the operational loop. However, this can significantly increase the size of a manageable state and complexity of network infrastructure.
As technology progresses, we find ourselves working with automated agents increasingly more often. Developing intelligent automated agents capable of interacting and operating in shared environments necessitate the development of integrative approaches which consider both the computational and human factors. In this talk, I will present a few of my research efforts towards developing intelligent agents with real-world impact, ranging from "adversarial" settings such as apprehending reckless drivers (which is currently
How well do current information systems serve us as individuals and as a society? The same systems celebrated for promoting free speech and equality only a decade ago, are now deemed a threat for democracy and a vector for polarization. Yet, much of this heated debate is neither grounded in empirical evidence nor constructive for building better systems for people.
Motion and activity recognition and characterization, plays a major role in our life. Activity includes body’s daily life activities, body’s gestures, and its more wide sense also facial expressions. Accurate characterization of the activity, can contribute to well-being by assisting in fields like sport, and in medicine, where it enable detect abnormalities in human behavior, estimate medical score in diseases like Huntington, and Parkinson diseases, and enable continuous monitoring of medical condition.
In this talk I consider two fundamental problems in statistical learning theory: how to choose a loss function, and how to address non-linear problems with linear tools.
Cloud computing opens a new chapter in information technology, by enabling global access to shared pools of resources such as services, data, servers, and computer networks. It drives new digital businesses across enterprises. In the last few years, an unprecedented amount of data center capacity has been built to support cloud computing services' growth.
Deep learning has become one of the leading methods of machine learning, with significant breakthroughs in the the domains of computer vision and speech recognition, among others. In this talk, I will describe some major obstacles, such as computation time and adversarial attacks, and present a number of possible directions we are taking to overcome these challenges.
