All Seminars
| Title: Hallucinating Analytics over Real-World Data using Augmented Reality |
|---|
| Seminar: Computer Science |
| Speaker: Dr. Arnab Nandi, The Ohio State University |
| Contact: Ymir Vigfusson, ymir@mathcs.emory.edu |
| Date: 2020-10-23 at 1:00PM |
| Venue: https://emory.zoom.us/j/92722816908 |
 Add to Calendar |
| Abstract: In addition to the virtual, there is a vast amount of data present in the real world. Given recent advances in computer vision, augmented reality, and cloud services, we are faced with a tremendous opportunity to augment the structured data around end-users with insights. Coinciding with these trends, the number of data-rich end-user activities is also rapidly increasing. Thus, it is useful to investigate the process of data exploration and analysis in augmented and mixed reality settings. In this talk, we describe a data exploration platform that utilizes augmented reality to enable querying over real-world data. Bio Arnab Nandi is an Associate Professor of Computer Science & Engineering at The Ohio State University. Arnab's work focuses on bridging human interaction and data infrastructure, spanning areas of database systems, human-in-the-loop data analytics, and next-generation query interfaces. At Ohio State, he co-founded the OHI/O Program, that fosters a tech culture through hackathons and informal learning, and The STEAM Factory, an interdisciplinary research and collaboration network. Arnab is a recipient of the US National Science Foundation's CAREER Award, a Google Faculty Research Award, and IEEE's TCDE Early Career Award for his contributions towards user-focused data interaction. Arnab holds a PhD in Computer Science & Engineering from the University of Michigan. |
| Title: Automated Testing and Precision Tuning of Numerical Software |
|---|
| Seminar: Computer Science |
| Speaker: Cindy Rubio Gonzalez, UC Davis |
| Contact: Dr. Dorian Arnold, Dorian.Arnold@emory.edu |
| Date: 2020-10-16 at 1:00PM |
| Venue: https://emory.zoom.us/j/92722816908 |
 Download Flyer Add to Calendar |
| Abstract: Abstract: The use of numerical software has grown rapidly over the past few years, providing the foundation for a large variety of applications including scientific software and machine learning. Given the variety of numerical errors that can occur, floating-point programs are difficult to write, test and debug. One common practice among developers is to use the highest available precision when allocating variables. While more robust, this can degrade program performance significantly. Furthermore, different levels of floating-point precision can lead to numerical inconsistencies that can be difficult to expose and diagnose. In this talk, I will describe our research on developing tools to assist programmers in tuning the precision of their floating-point programs as well as tools for testing numerical programs. I will conclude by discussing remaining challenges and opportunities for scalable precision tuning and testing of HPC applications. Bio:Cindy Rubio-Gonzalez is an Associate Professor of Computer Science at the University of California, Davis. Prior to joining UC Davis, she was a Postdoctoral Researcher in the EECS Department at the University of California, Berkeley. She received her Ph.D. in Computer Science from the University of Wisconsin--Madison in 2012. Her research spans the areas of Programming Languages and Software Engineering, with a focus on program analysis for automated bug finding and program optimization. She is particularly interested in the reliability and performance of systems software and scientific computing applications. Cindy is a recipient of several awards including the DOE Early Career Award, NSF CAREER Award, DOE Better Scientific Software Fellowship, Facebook Testing and Verification Research Award, UC Davis Hellman Fellowship, and UC Davis CAMPOS Faculty Award. |
| Title: Delivering the future of medical logistics -- behind the scenes at Zipline |
|---|
| Seminar: Computer Science |
| Speaker: Vasumathi Raman, Nuro (self-driving car) |
| Contact: Ymir Vigfusson, ymir@mathcs.emory.edu |
| Date: 2020-10-09 at 1:00PM |
| Venue: https://emory.zoom.us/j/92722816908 |
| Download Flyer Add to Calendar |
| Abstract: Abstract: Zipline is at the forefront of a logistics revolution, using autonomous aircraft to deliver just-in-time, lifesaving medical supplies on multiple continents, 7 days a week. We believe access to medical care should not depend on your GPS coordinates. This talk will introduce you to the tough engineering problems we solve in both hardware and software, and include a live (virtual) tour of one of our distribution centers in Ghana. We'll have plenty of time for questions. Bio: Vasu Raman is a roboticist who works on behaviour and motion planning for autonomous systems, and is passionate about transforming state-of-the-art concepts into robust real-world deployments. She is particularly driven by safety-critical systems performing complex tasks in dynamic environments, which require fusing technical and creative perspectives from control, machine learning, game theory, and formal methods. Vasu was an early engineer at both Zoox and Nuro, building planning and prediction for self-driving cars. She now works on detect-and-avoid technology at Zipline, realizing the future of on-demand logistics in medicine and beyond. Vasu has a PhD in CS from Cornell and a BA in Math and CS from Wellesley College. |
| Title: CSI PhD Student Summer Internship Reports |
|---|
| Seminar: Computer Science |
| Speaker: Various PhD Students, Emory University |
| Contact: Dr. Vaidy Sunderam, vss@emory.edu |
| Date: 2020-10-02 at 1:00PM |
| Venue: https://emory.zoom.us/j/92722816908 |
| Download Flyer Add to Calendar |
| Abstract: Student speakers will highlight their summer internship experiences, including their specific roles and projects as well as their higher level accomplishments, achievements and learning/growth outcomes. https://emory.zoom.us/j/92722816908 |
| Title: Improving Policy Learning via Programmatic Domain Knowledge |
|---|
| Seminar: Computer Science |
| Speaker: Yisong Yue, Cal Tech |
| Contact: Ymir Vigfusson, ymir@mathcs.emory.edu |
| Date: 2020-09-25 at 1:00PM |
| Venue: https://emory.zoom.us/j/92722816908 |
| Add to Calendar |
| Abstract: This talk explores how to leverage programmatic domain knowledge to improve policy learning (which includes reinforcement & imitation learning). I will consider two aspects. First, how can we express policy classes using domain specific programming languages to yield interesting inductive biases that lead to sample-efficient learning while preserving flexibility and improving interpretability? Second, building upon the data programming paradigm in supervised learning, how can we use expert-written programs as a form of auxiliary supervision to improve the reliability of policy learning? I will present problem framings, algorithms, and experiments for two settings: efficient learning of formally certified policies, and controllable generation of behaviors. Bio: Yisong Yue is a professor of Computing and Mathematical Sciences at the California Institute of Technology. He was previously a research scientist at Disney Research. Before that, he was a postdoctoral researcher in the Machine Learning Department and the iLab at Carnegie Mellon University. He received a Ph.D. from Cornell University and a B.S. from the University of Illinois at Urbana-Champaign. Yisong's research interests are centered around machine learning, and in particular getting theory to work in practice. To that end, his research agenda spans both fundamental and applied pursuits. In the past, his research has been applied to information retrieval, recommender systems, text classification, learning from rich user interfaces, analyzing implicit human feedback, data-driven animation, behavior analysis, sports analytics, experiment design for science, protein engineering, program synthesis, learning-accelerated optimization, robotics, and adaptive planning & allocation problems. |
| Title: CSI PhD Student Summer Internship Reports |
|---|
| Seminar: Computer Science |
| Speaker: Various, Emory University |
| Contact: Dr. Vaidy Sunderam, vss@emory.edu |
| Date: 2020-09-18 at 1:00PM |
| Venue: https://emory.zoom.us/j/92722816908 |
| Download Flyer Add to Calendar |
| Abstract: Student speakers will highlight their summer internship experiences, including their specific roles and projects as well as their higher level accomplishments, achievements and learning/growth outcomes. https://emory.zoom.us/j/92722816908 |
| Title: Understanding and Generating Human Language |
|---|
| Seminar: Computer Science |
| Speaker: Wei Xu, Georgia Institute of Technology |
| Contact: Jinho Choi, jinho.choi@emory.edu |
| Date: 2020-09-11 at 1:00PM |
| Venue: https://emory.zoom.us/j/92722816908 |
| Download Flyer Add to Calendar |
| Abstract: Human language is notoriously complex due to the multitude of ways people can express the same meaning. In this talk, I will present two series of work on machine learning methods to understand the varied expressions in human language and to generate paraphrases for applications, such as reading and writing assistive technology. In the first part, I will showcase how to design learning and ranking models for natural language generation, including a new metric that has been widely adopted as a learning objective and evaluation method. In the second part, I will present new datasets and a class of pairwise neural models for learning textural expressions that convey the same meaning. In contrast to previous work, we focus on extracting paraphrases on a much larger scale and with a much broader range by developing more robust models, leveraging social media data, and crowdsourcing. I will also briefly discuss the connections of my work to computational social science, language and code, and human language instructions. Bio: Wei Xu is an assistant professor in the School of Interactive Computing at the Georgia Institute of Technology. Before joining Georgia Tech, she was an assistant professor at The Ohio State University since 2016. Xu’s research interests are in natural language processing, machine learning, and social media. Her recent work focuses on language generation, paraphrase acquisition, semantic similarity models for language understanding. She has also worked on crowdsourcing and information extraction. She received her Ph.D. in Computer Science from New York University, B.S. and M.S. from Tsinghua University. She was a postdoctoral researcher at the University of Pennsylvania. She received an NSF CRII Award, a Best Paper Award at COLING 2018, CrowdFlower AI for Everyone Award, Criteo Faculty Research Award, as well as research funds from DARPA and IARPA. She recently served as a senior area chair for ACL 2020 and an area chair, workshop chair, and publicity chair for EMNLP and NAACL. She co-organizes the Workshop on Noisy User-generated Text annually. |
| Title: CSI PhD Student Summer Internship Reports |
|---|
| Seminar: Computer Science |
| Speaker: Various PhD Students, Emory University |
| Contact: Dr. Vaidy Sunderam, vss@emory.edu |
| Date: 2020-09-04 at 1:00PM |
| Venue: https://emory.zoom.us/j/92722816908 |
| Download Flyer Add to Calendar |
| Abstract: Student speakers will highlight their summer internship experiences, including their specific roles and projects as well as their higher level accomplishments, achievements and learning/growth outcomes. https://emory.zoom.us/j/92722816908 |
| Title: As We Are: Detecting and Mitigating Human Bias in Visual Analytics |
|---|
| Seminar: Computer Science |
| Speaker: Dr. Emily Wall, Emory University |
| Contact: TBA |
| Date: 2020-08-28 at 1:00PM |
| Venue: Zoom |
| Download Flyer Add to Calendar |
| Abstract: Visual Analytics combines the complementary strengths of humans (perception and sensemaking capabilities) and machines (fast and accurate information processing). However, people are susceptible to inherent limitations and biases, including cognitive biases (e.g., anchoring bias), social biases borne of cultural stereotypes and prejudices (e.g., gender bias), and perceptual biases (e.g., illusions). These biases can impact decision making in critical ways, leading to inaccurate or inefficient choices, or even propagating long-standing institutional and systemic biases. Given our knowledge of these biases and the increased use of data visualization for decision making, the goal of this research is to detect and mitigate human biases in visual data analysis. In this talk, I describe (1) which types of bias are particularly relevant in the process of visual data analysis, (2) how user interactions with data can be used to approximate human biases, and (3) how visualization systems can be designed to increase user awareness of potentially unconscious or implicit biases. By creating systems that promote real-time awareness of bias, people can reflect on their behavior and decision making and ultimately engage in a less-biased decision making process. Emily Wall is an Assistant Professor in the Computer Science department at Emory University (beginning Fall 2021). She completed her PhD in the School of Interactive Computing at Georgia Tech in 2020 and is currently a Postdoctoral Scholar at Northwestern University. Her research interests lie at the intersection of cognitive science and data visualization. Particularly, her research has focused on increasing awareness of unconscious and implicit human biases through the design and evaluation of (1) computational approaches to quantify bias from user interaction and (2) interfaces to support visual data analysis. Her research has been supported by NSF and Pacific Northwest National Laboratory, among others. |
| Title: CSI Graduate Panel featuring Drs. Dorian Arnold, Matthew Reyna, and Steve Qin |
|---|
| Seminar: Computer Science |
| Speaker: Dr. Arnold, Dr. Reyna, and Dr. Qin, Emory University |
| Contact: Dr. Sunderam, vss@emory.edu |
| Date: 2020-08-21 at 1:00PM |
| Venue: https://emory.zoom.us/j/92722816908 |
| Download Flyer Add to Calendar |
| Abstract: The CSI graduate program administrators will discuss ongoing CSI graduate program issues as well as Covid19-related Fall 2020 specifics. Please share your questions, comments, and suggestions, or email them in advance to the moderator Dr. Sunderam vss@emory.edu https://emory.zoom.us/j/92722816908 |