Select a calendar:
Filter November Events by Event Type:
SUNMONTUEWEDTHUFRISAT
Conferences, Lectures, & Seminars
Events for November
-
CS Colloquium: Klaus Havelund (NASA) - A Notation and System for Inferring Event Stream Abstractions
Tue, Nov 01, 2016 @ 04:00 PM - 05:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Klaus Havelund, NASA
Talk Title: A Notation and System for Inferring Event Stream Abstractions
Series: CS Colloquium
Abstract: This lecture satisfies requirements for CSCI 591: Computer Science Research Colloquium.
We propose a notation for specifying event stream abstractions for use in spacecraft telemetry processing. Our work is motivated by the need to quickly process streams with millions of events generated by the Curiosity rover on Mars. The approach builds a hierarchy of event abstractions for telemetry visualization and querying to aid human comprehension. Such abstractions can also be used as input to other runtime verification tools. Our notation is inspired by Allen's Temporal Logic, and provides a rule-based declarative way to express event abstractions. The system is written in Scala, with the specification language implemented as an internal DSL. It is based on parallel executing actors communicating via a publish-subscribe model. We illustrate the solution with several examples.
Biography: Klaus Havelund is a Senior Research Scientist at NASA's Jet Propulsion Laboratory (JPL), Pasadena, California. He has worked in the domain of software correctness for over three decades, and has worked at NASA for nearly two decades. He was affiliated with NASA Ames Research Center in Silicon Valley for eight years, before moving to JPL in Los Angeles. He has published over 120 papers and is an active member of the software verification research community. He special interests include techniques for monitoring actual systems behaviors, matching against expected behaviors, and more generally techniques for detecting errors in software programs.
Host: Chao Wang
Location: Henry Salvatori Computer Science Center (SAL) - 101
Audiences: Everyone Is Invited
Contact: Assistant to CS chair
-
CS Colloquium: Robert D. Nowak (University of Wisconsin-Madison) - A Notation and System for Inferring Event Stream Abstractions
Tue, Nov 08, 2016 @ 11:00 AM - 12:20 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Robert D. Nowak, University of Wisconsin-Madison
Talk Title: Learning Human Preferences and Perceptions From Data
Series: CS Colloquium
Abstract: This lecture satisfies requirements for CSCI 591: Computer Science Research Colloquium.
Modeling human perception has many applications in cognitive, social, and educational science, as well as in advertising and commerce. This talk discusses theory and methods for learning rankings and embeddings representing perceptions from datasets of human judgments, such as ratings or comparisons. I will briefly describe an ongoing large-scale experiment with the New Yorker magazine that deals with ranking cartoon captions using on our nextml.org system. Then I will discuss our recent work on ordinal embedding, also known as non-metric multidimensional scaling, which is the problem of representing items (e.g., images) as points in a low-dimensional Euclidean space given constraints of the form "item i is closer to item j than item k." In other words, the goal is to find a geometric representation of data that is faithful to comparative similarity judgments. This classic problem is often used to gauge and visualize perceptual similarities. A variety of algorithms exist for learning metric embeddings from comparison data, but the accuracy and performance of these methods were poorly understood. I will present a new theoretical framework that quantifies the accuracy of learned embeddings and indicates how many comparisons suffice as a function of the number of items and the dimension of the embedding. Furthermore, the theory points to new algorithms that outperform previously proposed methods. I will also describe a few applications of ordinal embedding.
This joint work with Lalit Jain and Kevin Jamieson.
http://nextml.org/assets/next.pdf
https://arxiv.org/pdf/1606.07081v1.pdf
Host: Yan Liu
Location: Ronald Tutor Hall of Engineering (RTH) - 526
Audiences: Everyone Is Invited
Contact: Assistant to CS chair
-
Amazon Information Session
Tue, Nov 08, 2016 @ 04:00 PM - 05:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: TBA, Amazon
Talk Title: Amazon Information Session
Series: CS Colloquium
Abstract: This lecture satisfies requirements for CSCI 591: Computer Science Research Colloquium.
IMDb is the world's most popular and authoritative source for movie, TV and celebrity content. IMDbPro https://secure.imdb.com/signup/index.html?r=/) is the essential resource for entertainment industry professionals. This membership-based service includes comprehensive information and tools that are designed to help entertainment industry professionals achieve success throughout all stages of their career. Additionally, IMDb owns and operates Withoutabox (https://www.withoutabox.com/), the premier submission service for film festivals and filmmakers, and Box Office Mojo (http://www.boxofficemojo.com/), the leading online box-office reporting service.
Please join us as a panel of industry experts discusses these and other exciting opportunities.
Biography: Unnati Sethi (moderator)
Unnati Sethi is a Software Development Manager at IMDb.com where she leads a team of engineers focused on deprecating legacy software and building highly interactive and creative end-user facing systems for film industry professionals. She has a Masters in Computer Science from the University of Southern California and over fifteen years of experience building software with cross-geographical, multi-cultural teams of varying sizes. She is a vocal advocate for diversity in the technology and entertainment industry and is actively involved in recruitment and diversity outreach initiatives at IMDb and Amazon.
Marty Bower
Marty has over 20 years of experience as a software development engineer and a software development manager, building applications and leading teams in full lifecycle software development. He's worked at IMDb since January of this year, and previously for large financial technology companies like Intuit. He enjoys leading a team in developing an application that is revolutionizing how film festivals process and judge submissions, and help filmmakers get discovered.
Shlomi Yehezkel
Shlomi has been with Amazon for 4+ years now; he joined Amazon as an SDE and has worked with 3 different teams: first with Ad Analytics, where he was responsible for analyzing the performance of advertisements campaigns, then with Amazon Payments, where he worked with the gift card team and, finally, his current position with IMDbPro where he owns the back end systems. Shlomi transitioned to being a Software Development Manager on IMDbPro earlier this year.
Shlomi loves to work on the logic layer which is the layer between the presentation layer to the data layer.
Jerome Core
Jerome is the Customer Service Manager for all IMDb brands. Jerome joined the team in 2014, bringing over ten years of customer service experience. A native Angelino, Jerome has worked with many ecommerce businesses including Internet Brands, Campus Explorer, and online fashion retailer Farfetch.com
Bishnu Kumar
Bishnu is a Sr. Product Manager at IMDb who manages the IMDbPro business. Bishnu joined Amazon Customer Return team in Seattle in 2015 and internally-transferred to the IMDb LA team last month. In 2014 he was a MBA intern in Amazon and prior to that he worked at Samsung in the software development and commercialization of Android handsets.
Christian Sosa-lanz
Christian has been at Amazon for 2 years, working with the Withoutabox team. Prior to that he has been working in the UX field for 15 years designing Disney MagicBands, NordstromRack and physical interfaces. On his off time, he digs into architecture and tinkers with IoT.
Host: CS Department
Location: Henry Salvatori Computer Science Center (SAL) - 101
Audiences: Everyone Is Invited
Contact: Assistant to CS chair
-
CS Colloquium: Hal Daumé III (UMD) - Learning Language through Interaction
Mon, Nov 14, 2016 @ 12:00 PM - 01:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Hal Daumé III, UMD
Talk Title: Learning Language through Interaction
Series: Yahoo! Labs Machine Learning Seminar Series
Abstract: This lecture satisfies requirements for CSCI 591: Computer Science Research Colloquium. Part of Yahoo! Labs Machine Learning Seminar Series.
Machine learning-based natural language processing systems are amazingly effective, when plentiful labeled training data exists for the task/domain of interest. Unfortunately, for broad coverage (both in task and domain) language understanding, we're unlikely to ever have sufficient labeled data, and systems must find some other way to learn. I'll describe a novel algorithm for learning from interactions, and several problems of interest, most notably machine simultaneous interpretation (translation while someone is still speaking). This is all joint work with some amazing (former) students He He, Alvin Grissom II, John Morgan, Mohit Iyyer, Sudha Rao and Leonardo Claudino, as well as colleagues Jordan Boyd-Graber, Kai-Wei Chang, John Langford, Akshay Krishnamurthy, Alekh Agarwal, Stéphane Ross, Alina Beygelzimer and Paul Mineiro.
Biography: Hal Daume III is an associate professor in Computer Science at the University of Maryland, College Park. He holds joint appointments in UMIACS and Linguistics. He was previously an assistant professor in the School of Computing at the University of Utah. His primary research interest is in developing new learning algorithms for prototypical problems that arise in the context of language processing and artificial intelligence. This includes topics like structured prediction, domain adaptation and unsupervised learning; as well as multilingual modeling and affect analysis. He associates himself most with conferences like ACL, ICML, NIPS and EMNLP. He earned his PhD at the University of Southern California with a thesis on structured prediction for language (his advisor was Daniel Marcu). He spent the summer of 2003 working with Eric Brill in the machine learning and applied statistics group at Microsoft Research. Prior to that, he studied math (mostly logic) at Carnegie Mellon University.
Host: Yan Liu
Location: Seeley G. Mudd Building (SGM) - 123
Audiences: Everyone Is Invited
Contact: Assistant to CS chair
-
CS Colloquium and RASC Seminar: Subramanian Ramamoorthy (University of Edinburgh) -Representations and Models for Collaboratively Intelligent Robots
Tue, Nov 15, 2016 @ 03:30 PM - 05:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Subramanian Ramamoorthy, University of Edinburgh
Talk Title: Representations and Models for Collaboratively Intelligent Robots
Series: RASC Seminar Series
Abstract: This lecture satisfies requirements for CSCI 591: Computer Science Research Colloquium.
We are motivated by the problem of building autonomous robots that are able to work collaboratively with other agents, such as human co-workers. One key attribute of such an autonomous system is the ability to make predictions about the actions and intentions of other agents in a dynamic environment - both to interpret the activity context as it is being played out and to adapt actions in response to that contextual information.
Drawing on examples from robotic systems we have developed in my lab, including mobile robots that can navigate effectively in crowded spaces and humanoid robots that can cooperate in assembly tasks, I will present recent results addressing the questions of how to efficiently capture the hierarchical nature of activities, and how to rapidly estimate latent factors, such as hidden goals and intent.
Firstly, I will describe a procedure for topological trajectory classification, using the concept of persistent homology, which enables unsupervised extraction of certain kinds of relational concepts in motion data. One use of this representation is in devising a multi-scale version of Bayesian recursive estimation, which is a step towards reliably grounding human instructions in the realized activity.
Finally, I will describe work with a human-robot interface based on the combined use of vision and mobile 3D eye tracking as a signal for inference about fixation programs. Formulating this in terms of a probabilistic generative model, we estimate fixation locations within a 3D scene, which in turn allows us to associate symbols in a higher level plan with the actual appearance of novel objects that the symbols refer to.
Biography: Dr. Subramanian Ramamoorthy is a Reader (Associate Professor) in the School of Informatics, University of Edinburgh, where he has been on the faculty since 2007. He is a Coordinator of the EPSRC Robotarium Research Facility in the School of Informatics, and Executive Committee Member for Edinburgh Centre for Robotics. He received his PhD in Electrical and Computer Engineering from The University of Texas at Austin in 2007. He is an elected Member of the Young Academy of Scotland at the Royal Society of Edinburgh, and has held Visiting Professor positions at the Precourt Institute for Energy at Stanford University and at the University of Rome "La Sapienza".
His research focus has been on robot learning and decision-making under uncertainty, with emphasis on problems involving human-robot and multi-robot collaborative activities. These problems are solved using a combination machine learning techniques with emphasis on issues of transfer, online and reinforcement learning as well as new representations and analysis techniques based on geometric/topological abstractions.
His work has been recognised by nominations for Best Paper Awards at major international conferences - ICRA 2008, IROS 2010, ICDL 2012 and EACL 2014. He serves in editorial and programme committee roles for conferences and journals in the areas of AI and Robotics. He leads Team Edinferno, the first UK entry in the Standard Platform League at the RoboCup International Competition. This work has received media coverage, including by BBC News and The Telegraph, and has resulted in many public engagement activities, such as at the Royal Society Summer Science Exhibition, Edinburgh International Science festival and Edinburgh Festival Fringe.
Before joining the School of Informatics, he was a Staff Engineer with National Instruments Corp., where he contributed to five products in the areas of motion control, computer vision and dynamic simulation. This work resulted in seven US patents and numerous industry awards for product innovation.
Host: Gaurav Sukhatme
Location: Henry Salvatori Computer Science Center (SAL) - 101
Audiences: Everyone Is Invited
Contact: Assistant to CS chair
-
CS Colloquium: Arindam Banerjee (University of Minnesota, Twin Cities) - Learning with Low Samples in High-Dimensions: Estimators, Geometry, and Applications
Thu, Nov 17, 2016 @ 04:00 PM - 05:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Arindam Banerjee, University of Minnesota, Twin Cities
Talk Title: Learning with Low Samples in High-Dimensions: Estimators, Geometry, and Applications
Series: Yahoo! Labs Machine Learning Seminar Series
Abstract: This lecture satisfies requirements for CSCI 591: Computer Science Research Colloquium. Part of Yahoo! Labs Machine Learning Seminar Series.
Many machine learning problems, especially scientific problems in areas such as ecology, climate science, and brain sciences, operate in the so-called `low samples, high dimensions' regime. Such problems typically have numerous possible predictors or features, but the number of training examples is small, often much smaller than the number of features. In this talk, we will discuss recent advances in general formulations and estimators for such problems. These formulations generalize prior work such as the Lasso and the Dantzig selector. We will discuss the geometry underlying such formulations, and how the geometry helps in establishing finite sample properties of the estimators. We will also discuss applications of such results in structure learning in probabilistic graphical models, along with real world applications in ecology and climate science.
This is joint work with Soumyadeep Chatterjee, Sheng Chen, Farideh Fazayeli, Andre Goncalves, Jens Kattge, Igor Melnyk, Peter Reich, Franziska Schrodt, Hanhuai Shan, and Vidyashankar Sivakumar.
Biography: Arindam Banerjee is an Associate Professor at the Department of Computer & Engineering and a Resident Fellow at the Institute on the Environment at the University of Minnesota, Twin Cities. His research interests are in statistical machine learning and data mining, and applications in complex real-world problems including climate science, ecology, recommendation systems, text analysis, brain sciences, finance, and aviation safety. He has won several awards, including the Adobe Research Award (2016), the IBM Faculty Award (2013), the NSF CAREER award (2010), and six Best Paper awards in top-tier conferences.
Host: Yan Liu
Location: Henry Salvatori Computer Science Center (SAL) - 101
Audiences: Everyone Is Invited
Contact: Assistant to CS chair
-
CS Colloquium and CAIS Seminar: Nicole Immorlica (Microsoft Research) - Maximizing the Social Good: Markets without Money
Fri, Nov 18, 2016 @ 12:00 PM - 01:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Nicole Immorlica, Microsoft Research
Talk Title: Maximizing the Social Good: Markets without Money
Series: Center for AI in Society (CAIS) Seminar Series
Abstract: This lecture satisfies requirements for CSCI 591: Computer Science Research Colloquium.
To create a truly sustainable world, we need to both generate ample amounts of resources and allocate them appropriately to those that value them highly. In traditional economics, these goals are achieved using money. People are paid to produce valuable resources. Resources are sold at an appropriately high price, guaranteeing that the buyers had high value for them. However, in many settings of particular social significance, monetary transactions are infeasible. Sometimes this is because society has deemed it immoral to sell certain things, like seats at public schools or organs for transplantation. Other times it is because of technological constraints, like when the environment is electronic and there are no banks linked to user accounts.
In this talk, we will discuss two alternatives to money -- risk and social status -- and apply them to school choice and user-generated content websites. Risk is useful to help determine a person's value for a resource: the more someone is willing to risk for something, the more they value it. Using this insight, we propose an algorithm to allocate seats at public schools to students who value them the most. Social status is useful to motivate people to contribute to a public project. Using this insight, we design badges and leaderboards to maximize contributions to user-generated content websites like citizen science projects, question-and-answering sites, or review sites.
Host: CS Department
Location: Seeley G. Mudd Building (SGM) - 123
Audiences: Everyone Is Invited
Contact: Assistant to CS chair
-
CS Colloquium: Richard Samworth (University of Cambridge) - High-dimensional changepoint estimation via sparse projection
Tue, Nov 29, 2016 @ 04:00 PM - 05:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Richard Samworth, University of Cambridge
Talk Title: High-dimensional changepoint estimation via sparse projection
Series: Yahoo! Labs Machine Learning Seminar Series
Abstract: This lecture satisfies requirements for CSCI 591: Computer Science Research Colloquium. Part of Yahoo! Labs Machine Learning Seminar Series.
Changepoints are a very common feature of Big Data that arrive in the form of a data stream. We study high-dimensional time series in which, at certain time points, the mean structure changes in a sparse subset of the coordinates. The challenge is to borrow strength across the coordinates in order to detect smaller changes than could be observed in any individual component series. We propose a two-stage procedure called 'inspect' for estimation of the changepoints: first, we argue that a good projection direction can be obtained as the leading left singular vector of the matrix that solves a convex optimisation problem derived from the CUSUM transformation of the time series. We then apply an existing univariate changepoint detection algorithm to the projected series. Our theory provides strong guarantees on both the number of estimated changepoints and the rates of convergence of their locations, and our numerical studies validate its highly competitive empirical performance for a wide range of data generating mechanisms.
Biography: I am a Professor of Statistics in the Statistical Laboratory, a sub-department of the Department of Pure Mathematics and Mathematical Statistics. This is part of the Faculty of Mathematics at the University of Cambridge. I am also a Teaching Fellow at St John's College, and run the Statistics Clinic for members of the university.
I currently hold a five-year EPSRC Early Career Fellowship, which began on 1 December 2012. I am also an Alan Turing Institute Faculty Fellow.
Host: Yan Liu
Location: Henry Salvatori Computer Science Center (SAL) - 101
Audiences: Everyone Is Invited
Contact: Assistant to CS chair
-
CS Colloquium: Grace Hui Yang (Georgetown University) - Statistical Modeling of Information Seeking
Wed, Nov 30, 2016 @ 02:30 PM - 03:30 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Grace Hui Yang , Georgetown University
Talk Title: Statistical Modeling of Information Seeking
Series: CS Colloquium
Abstract: Many modern IR systems and data exhibit new characteristics which are largely ignored by conventional techniques. What is missing is an ability for the model to change over time and be responsive to stimulus. Documents, relevance, users and tasks all exhibit dynamic behavior that is captured in big data sets (typically collected over long time spans) and models need to respond to these changes. This talk provides an up-to-date introduction to statistical modeling of information seeking. In particular, I will talk about how we model information seeking as a partially observable Markov decision process and achieve high accuracy in the TREC Session Tracks. I will also talk about evaluation in dynamic information retrieval modeling and the TREC Dynamic Domain Track.
Biography: Grace Hui Yang is an Assistant Professor in the Department of Computer Science at Georgetown University. Grace obtained her Ph.D. from the Language Technologies Institute, Carnegie Mellon University in 2011. Grace's current research interests include dynamic search, search engine evaluation, privacy-preserving information retrieval, and information organization. Prior to this, she conducted research on question answering, ontology construction, near-duplicate detection, multimedia information retrieval and opinion and sentiment detection. Grace is a recipient of the National Science Foundation (NSF) Faculty Early Career Development Program (CAREER) Award. Grace co-chaired the SIGIR 2013-2014 Doctoral Consortium, SIGIR 2017 Workshop, and WSDM 2017 Workshop. She served as an area chair for SIGIR 2014-2017 and ACL 2016. Grace also co-organized the TREC Dynamic Domain Track since 2015.
Host: Cyrus Shahabi
Location: Olin Hall of Engineering (OHE) - 100C
Audiences: Everyone Is Invited
Contact: Assistant to CS chair
