Select a calendar:
Filter March Events by Event Type:
SUNMONTUEWEDTHUFRISAT
Events for March 28, 2016
-
CS Colloquium: David Fouhey (CMU) -Towards A Physical and Human-Centric Understanding of Images
Mon, Mar 28, 2016 @ 11:00 AM - 12:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: David Fouhey, CMU
Talk Title: Towards A Physical and Human-Centric Understanding of Images
Series: CS Colloquium
Abstract: This lecture satisfies requirements for CSCI 591: Computer Science Research Colloquium
One primary goal of AI from its very beginning has been to develop systems that can understand an image in a meaningful way. While we have seen tremendous progress in recent years on naming-style tasks like image classification or object detection, a meaningful understanding requires going beyond this paradigm. Scenes are inherently 3D, so our understanding must also capture the underlying 3D and physical properties. Additionally, our understanding must be human-centric since any man-made scene has been built with humans in mind. Despite the importance of obtaining a 3D and human-centric understanding, we are only beginning to scratch the surface on both fronts: many fundamental questions, in terms of how to both frame and solve the problem, remain unanswered.
In this talk, I will discuss my efforts towards building a physical and human-centric understanding of images. I will present work addressing the questions: (1) what 3D properties should we model and predict from images, and do we actually need explicit 3D training data to do this? (2) how can we reconcile data-driven learning techniques with the physical constraints that exist in the world? and (3) how can understanding humans improve traditional 3D and object recognition tasks?
Biography: David Fouhey is a Ph.D. student at the Robotics Institute of Carnegie Mellon University, where he is advised by Abhinav Gupta and Martial Hebert. His research interests include computer vision and machine learning with a particular focus on scene understanding. David's work has been supported by both NSF and NDSEG fellowships. He has spent time at Microsoft Research and University of Oxford's Visual Geometry Group.
Host: CS Department
Location: Olin Hall of Engineering (OHE) - 136
Audiences: Everyone Is Invited
Contact: Assistant to CS chair
-
CS Colloquium: Tuo Zhao (Johns Hopkins University) - Compute Faster and Learn Better: Machine Learning via Nonconvex Model-based Optimization
Mon, Mar 28, 2016 @ 03:00 PM - 04:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Tuo Zhao , Johns Hopkins University
Talk Title: Compute Faster and Learn Better: Machine Learning via Nonconvex Model-based Optimization
Series: CS Colloquium
Abstract: This lecture satisfies requirements for CSCI 591: Computer Science Research Colloquium
Nonconvex optimization naturally arises in many machine learning problems (e.g. sparse learning, matrix factorization, and tensor decomposition). Machine learning researchers exploit various nonconvex formulations to gain modeling flexibility, estimation robustness, adaptivity, and computational scalability. Although classical computational complexity theory has shown that solving nonconvex optimization is generally NP-hard in the worst case, practitioners have proposed numerous heuristic optimization algorithms, which achieve outstanding empirical performance in real-world applications.
To bridge this gap between practice and theory, we propose a new generation of model-based optimization algorithms and theory, which incorporate the statistical thinking into modern optimization. Particularly, when designing practical computational algorithms, we take the underlying statistical models into consideration (e.g. sparsity, low rankness). Our novel algorithms exploit hidden geometric structures behind many nonconvex optimization problems, and can obtain global optima with the desired statistics properties in polynomial time with high probability.
Biography: Tuo Zhao is a PhD student in Department of Computer Science at Johns Hopkins University (http://www.cs.jhu.edu/~tour). His research focuses on high dimensional parametric and semiparametric learning, large-scale optimization, and applications to computational genomics and neuroimaging. He was the core member of the JHU team winning the INDI ADHD 200 global competition on fMRI imaging-based diagnosis classification in 2011. He received Siebel scholarship in 2014 and Baidu's research fellowship in 2015
Host: CS Department
More Info: https://bluejeans.com/741584974
Location: Ronald Tutor Hall of Engineering (RTH) - 526
Audiences: Everyone Is Invited
Contact: Assistant to CS chair
Event Link: https://bluejeans.com/741584974
-
CS Colloquium: Bogdan Vasilescu (UC Davis) - Lessons in Social Coding: Software Analytics in the Age of GitHub
Mon, Mar 28, 2016 @ 04:00 PM - 05:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Bogdan Vasilescu, UC Davis
Talk Title: Lessons in Social Coding: Software Analytics in the Age of GitHub
Series: CS Colloquium
Abstract: This lecture satisfies requirements for CSCI 591: Computer Science Research Colloquium
Social media has forever changed the ways in which we communicate and work, programming included. This "social coding" movement (code is meant to be shared!) made popular by GitHub has come to represent a paradigm shift in software development, especially in the open-source world. For example, the "pull request" model has made it easier than ever before for newcomers to submit contributions to a project. As a result, teams are becoming increasingly larger, more distributed, and more diverse. At the same time, the incentives for contributing have evolved. For example, one's social coding activity is starting to replace one's resume, and directly influence their hourly wage. Today, GitHub reports 12 million users and over 30 million repositories, with popular projects having communities the size of small cities. These numbers are unprecedented in open-source!
This new, social way of developing software opens a great many questions. How do people choose which projects to contribute to? Does prior technical experience matter, or do people learn on the job? Is it efficient to work on many projects in parallel? How does diversity in software teams affect productivity and code quality? What are the main factors that slow down pull request reviews? How does automation help developers do more with less? Does continuous integration help to ensure higher quality code? I will try to answer some of these questions in this talk.
Biography: Bogdan Vasilescu is currently a postdoctoral researcher at University of California, Davis (USA), where he is a member of the Davis Eclectic Computational Analytics Lab (DECAL). He received his PhD and MSc in Computer Science at Eindhoven University of Technology, both with cum laude distinction. His PhD dissertation won the best dissertation award from the Dutch Institute for Programming Research and Algorithmics in 2015. Follow him on Twitter @b_vasilescu
Host: CS Department
More Info: https://bluejeans.com/958446198
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 248
Audiences: Everyone Is Invited
Contact: Assistant to CS chair
Event Link: https://bluejeans.com/958446198
