Select a calendar:
Filter May Events by Event Type:
SUNMONTUEWEDTHUFRISAT
Events for May 13, 2015
-
Teamcore Seminar: Dr. William Haskell (National University of Singapore) - Approximate Dynamic Programming
Wed, May 13, 2015 @ 10:30 AM - 11:30 AM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Dr. William Haskell, National University of Singapore
Talk Title: Approximate Dynamic Programming
Series: Teamcore Seminar
Abstract: We develop a new technique for analyzing the convergence of stochastic algorithms. This technique is based on the notion of stochastic dominance and allows us to get sample complexity results. We apply this technique to study the convergence of several approximate dynamic programming algorithms for MDPs on continuous state spaces, as well as to propose some new algorithms.
Biography: Dr. William Haskell is an assistant professor in the department of the industrial & systems engineering at National University of Singapore. He obtained a PhD from the department of industrial engineering and operation research from UC Berkeley. He was a visiting scholar at USC ISE department from August 2011 to May 2013 and then a Postdoctoral Research Associate from June 2011 to May 2014 at the USC EE and CS department. His research has focused on risk-aware decision making, sequential and large-scale optimization and data-driven decision making.
Host: Teamcore Research Group
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 248
Audiences: Everyone Is Invited
Contact: Assistant to CS chair
-
AI Seminar: Computerized Search for Causal Relations in High Dimensional Data: Some Results and Many Problems
Wed, May 13, 2015 @ 11:00 AM - 12:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Clark Glymour , Alumni University Professor, Carnegie Mellon University
Talk Title: Computerized Search for Causal Relations in High Dimensional Data: Some Results and Many Problems
Series: Artificial Intelligence Seminar
Abstract: I will briefly review the graphical causal model framework and describe some of the search strategies that have proved practical in small dimensional problems. Then I will describe some of the modifications we have recently pursued at Carnegie Mellon to allow search in high dimensional problems, e.g, 50.000 - 1,000,000 variables, with sample sizes orders of magnitude smaller, and some of the many problems we have not satisfactorily solved.
Biography: Clark Glymour is the Alumni University Professor in the Department of Philosophy at Carnegie Mellon University. He is also a senior research scientist at the Florida Institute for Human and Machine Cognition. He is the founder of the Philosophy Department at Carnegie Mellon University, a Guggenheim Fellow, a Fellow of the Center for Advanced Study in Behavioral Sciences a Phi Beta Kappa lecturer, and is a Fellow of the statistics section of the AAAS. Glymour and his collaborators created the causal interpretation of Bayes nets and developed an automated causal inference algorithm implemented as software named TETRAD. His areas of interest include epistemology (particularly Android epistemology), machine learning, automated reasoning, psychology of judgment, and mathematical psychology.
Host: Kun Zhang
More Info: http://webcasterms1.isi.edu/mediasite/Viewer/?peid=ebaa5ed5e1444cbfa7aea272f321509d1d
Webcast: http://webcasterms1.isi.edu/mediasite/Viewer/?peid=ebaa5ed5e1444cbfa7aea272f321509d1dLocation: Information Science Institute (ISI) - 11th Flr Conf Rm # 1135, Marina Del Rey
WebCast Link: http://webcasterms1.isi.edu/mediasite/Viewer/?peid=ebaa5ed5e1444cbfa7aea272f321509d1d
Audiences: Everyone Is Invited
Contact: Peter Zamar
Event Link: http://webcasterms1.isi.edu/mediasite/Viewer/?peid=ebaa5ed5e1444cbfa7aea272f321509d1d
-
Communications, Networks & Systems (CommNetS) Seminar
Wed, May 13, 2015 @ 02:00 PM - 03:00 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Dr. Frank C. Langbein, Cardiff University
Talk Title: Controlling Information Transfer in Spintronics Networks
Series: CommNetS
Abstract: The propagation of information encoded in spin degrees of freedom through networks of coupled spins enables important applications in spintronics and quantum information processing. Control is required to direct the flow of information through a spintronic network in an efficient manner, e.g for an on-chip interconnect or for routing quantum information. In principle information stored in spin states can propagate through a network of coupled spins without any charge transport. As propagation of spin-based information is governed by quantum-mechanics and the Schrodinger equation, excitations in a spin network propagate, disperse and refocus in a wave-like manner. We study control of information propagation in rings of spins as a simple prototype of a router for spin-based information. For our purposes we restrict ourselves to spin-1/2 particles with uniform nearest neighbour couplings forming a ring with a single excitation (or one bit) in the network. Control can be utilised to maximise transfer efficiency and speed of this excitation. We specifically consider optimising spatially distributed potentials, which remain constant during the evolution, in contrast to dynamic control schemes, which require dynamic modulation or fast switching of the control potentials. Due to the limited degrees of freedom in the system, finding a control that maximises the transfer probability in a short time is difficult, but in principle simplifies the implementation of the routing scheme. For practical implementation of such a scheme specific network structures and spin coupling strengths will have to be identified from measurements of actual devices to build a model suitable to find the necessary controls. For this we present an approach for discriminating between different network structures and learning model parameters.
Biography: Frank C Langbein is a lecturer in computer science at Cardiff University, leading the Quantum Technologies Group, and is a member of the Geometric Computing and Computer Vision research group. He is also a member of the Research Institute for Visual Computing where he is co-leading the sub-programme on vision-based geometric modelling and the interface with science. He received a diploma in mathematics from Stuttgart University in 1998 and a PhD from Cardiff University in 2003.
He is working on computational and geometric modelling, control, machine learning and visual computing with applications in quantum technologies, healthcare, mechanical and chemical engineering and spintronics.
Host: Prof. Edmond Jonckheere
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 248
Audiences: Everyone Is Invited
Contact: Annie Yu
