Situated Intelligent Interactive Systems
Dr. Zhou Yu
Communication is an intricate dance, an ensemble of coordinated individual actions. Imagine a future where machines interact with us like humans, waking us up in the morning, navigating us to work, or discussing our daily schedules in a coordinated and natural manner. Current interactive systems being developed by Apple, Google, Microsoft, and Amazon attempt to reach this goal by combining a large set of single-task systems. But products like Siri, Google Now, Cortana and Echo still follow pre-specified agendas that cannot transition between tasks smoothly and track and adapt to different users naturally. My research draws on recent developments in speech and natural language processing, human-computer interaction, and machine learning to work towards the goal of developing *situated intelligent interactive systems*. These systems can coordinate with users to achieve effective and natural interactions. I have successfully applied the proposed concepts to various tasks, such as visual dialog, customer service, social conversation, job interview training and movie promotion. Our team recently was selected as one out of the 8 groups to compete in Amazon Alexa Prize Challenge with $250,000. Our group also received research awards and gifts from various companies, such as Intel, Tencent and Bosh.
Dr. Zhou Yu is an Assistant Professor at the Computer Science Department in UC Davis. She received her PhD in the Language Technology Institute under School of Computer Science, Carnegie Mellon University in 2017. She was recently featured in Forbes as 2018 30 under 30 in Science. She was also a recipient of Rising stars in EECS in 2015. Dr. Yu received a B.S. in Computer Science and a B.A. in Linguistics from Zhejiang University in 2011.
Intelligent Software Engineering: Synergy between AI and Software Engineering
Dr. Tao Xie, University of Illinois at Urbana-Champaign, ACM Distinguished Speaker
Research and practice on leveraging or adapting AI technologies for addressing software engineering tasks especially on tool automation have been around for decades. Recent efforts from the research community have been on addressing a series of questions, e.g., how to define or determine levels of intelligence in software engineering tools, how to bring high levels of intelligence in software engineering tools, how to synergically integrate machine intelligence and human intelligence (e.g., domain knowledge or insight) to effectively tackle challenging software engineering tasks. On the other hand, given the increasing importance and popularity of AI software in the society, recent efforts from the research community have been also on exploring software engineering solutions to improve the productivity of developing AI software and the dependability of AI software. The emerging field of intelligent software engineering is to focus on two directions:
- Instilling intelligence in solutions for software engineering tasks
- Providing software engineering solutions for AI software
This talk will share perspectives on intelligent software engineering along with some example research on the two directions in intelligent software engineering.
Tao Xie is a Professor and Willett Faculty Scholar in the Department of Computer Science at the University of Illinois at Urbana-Champaign, USA. He worked as a visiting researcher at Microsoft Research. His research interests are in software engineering, focusing on software testing, program analysis, software analytics, software security, and educational software engineering. He received an NSF CAREER Award, a Microsoft Research Outstanding Collaborators Award, a Google Faculty Research Award, an IBM Jazz Innovation Award, and three-time IBM Faculty Awards. He is an ACM Distinguished Speaker and was an IEEE Computer Society Distinguished Visitor. He is an ACM Distinguished Scientist and an IEEE Fellow. His homepage is at http://taoxie.cs.illinois.edu
NASA's Juno Mission to Jupiter: What's Inside the Giant Planet?
Dr. Fran Bagenal Professor of Astrophysical and Planetary Sciences and Research Scientist, Laboratory of Atmospheric and Space Physics, University of Colorado, Boulder
Launched in August, 2011, Juno's principal goal is to understand the origin and evolution of Jupiter. Underneath its dense cloud cover, Jupiter safeguards secrets to the fundamental processes and conditions that governed the formation of our solar system. As our primary example of a giant planet, Jupiter can also provide critical knowledge for understanding the planetary systems being discovered around other stars. Juno probes the existence of a solid planetary core, maps Jupiter’s intense magnetic field, and gauges the amount of water and ammonia in the deep atmosphere. Most inspirational: thousands of citizen scientists process stunning pictures snapped by the onboard JunoCam. Achieving polar orbit on the 4th of July, 2016, Juno is the first to fly over the Jovian aurora; the craft measures energetic particles raining down on the planet as well as the northern and southern lights that these particles excite. Dr. Bagenal will review how scientists use radio-band Doppler shift for gravity sounding, the way that microwave absorption provides information about atmospheric composition, and how fusing ultraviolet and infrared images with radio and plasma data reveals the process of auroral emissions.
Dr. Fran Bagenal studied physics and geophysics at the University of Lancaster. Inspired by NASA's missions to Mars and the prospect of the Voyager mission, she pursued graduate studies at MIT. Her 1981 PhD thesis analyzed data from the Voyager Plasma Science experiment in Jupiter's magnetosphere. She spent 1982 through 1987 as a post-doctoral researcher in space physics at Imperial College, London. Voyager flyby's of Uranus and Neptune brought her back to the United States: in 1989 she joined the faculty at the University of Colorado, Boulder. In addition to Voyager, Professor Bagenal has contributed to the Galileo mission to Jupiter and to the Deep Space 1 mission to Comet Borrelly. She heads the plasma teams for Juno and New Horizons, the first launches in NASA's New Frontiers program. After a 9.5-year flight, New Horizons flew past Pluto on July 14, 2015.
Cybersecurity Risk in Modern Power Systems
This seminar will cover, in simple terms, why modern power systems (the "Smart Grid"), and cyber-physical systems in general, are at increased risk for cyberattack. We will discuss a real-world scenario in the California grid and how we can evaluate possible cyber issues with the technology. We will also discuss the technical expertise necessary for the next generation of cyber-power professionals to solve problems and mitigate risk.
Thomas (Tom) Williams is the Security Architect for the California Independent System Operator (ISO). Tom holds a Master of Science in Information Security & Assurance from Western Governors University and a Master of Business Administration from Golden Gate University. Tom's professional certifications include CISSP and TOGAF.
Stochastic Models in Robotics
Many stochastic problems of interest in engineering and science involve random, rigid-body motions. In this talk, a variety of stochastic phenomena that evolve on the group of rigid-body motions will be discussed together with tools from harmonic analysis and Lie theory to solve the associated equations. These phenomena include mobile robot path planning and camera calibration. Current work on multi-robot team diagnosis and repair, information fusion, and self-replicating robots will also be discussed. In order to quantify the robustness of such robots, measures of the degree of environmental uncertainty that they can handle need to be computed. The entropy of the set of all possible arrangements (or configurations) of spare parts in the environment is one example of such a measure and has led us to study problems at the foundations of statistical mechanics and information theory. These and other topics in robotics lend themselves to the same mathematical tools, which also will be discussed in this talk.
Gregory S. Chirikjian received undergraduate degrees from Johns Hopkins University in 1988, and a Ph.D. degree from the California Institute of Technology, Pasadena, in 1992. Since 1992, he has served on the faculty of the Department of Mechanical Engineering at Johns Hopkins University, attaining the rank of full professor in 2001. Additionally, from 2004-2007, he served as department chair.
Chirikjian’s research interests include robotics, applications of group theory in a variety of engineering disciplines, and the mechanics of biological macromolecules. He is a 1993 National Science Foundation Young Investigator, a 1994 Presidential Faculty Fellow, and a 1996 recipient of the ASME Pi Tau Sigma Gold Medal. In 2008, Chirikjian became a fellow of the ASME, and in 2010, he became a fellow of the IEEE. From 2014-15, he served as a program director for the National Robotics Initiative, which included responsibilities in the Robust Intelligence cluster in the Information and Intelligent Systems Division of CISE at NSF. Chirikjian is the author of more than 250 journal and conference papers and the primary author of three books, including Engineering Applications of Noncommutative Harmonic Analysis (2001) and Stochastic Models, Information Theory, and Lie Groups, Vols. 1+2. (2009, 2011). In 2016, an expanded edition of his 2001 book was published as a Dover book under a new title, Harmonic Analysis for Engineers and Applied Scientists.
How To Develop Cybersecurity Athletes
In 10 years cybersecurity competitions will be as popular for students in middle school, high school and college as traditional sports. This presentation shows how and why cybersecurity athletes will provide talent and numbers needed to help meet industry and government workforce needs. Cybersecurity competitions provide an ongoing virtual training ground for participants to develop, practice and validate their cybersecurity knowledge and skills using high-fidelity simulation environments. Those who participate in cyber competitions are athletes with the same training, passion and coolness as traditional physical athletes. However, there are more opportunities for these cyber athletes to go pro. Not only do participants practice their computing talents, but they also learn intangible skills such as problem-solving, teamwork and communications. Each ability is valuable for individuals looking to launch a career in cybersecurity.
Dr. Dan Manson is a Professor in Computer Information Systems (CIS) at California State Polytechnic University, Pomona (Cal Poly Pomona). Dr. Manson has also served as the CIS Department Chair and Campus Information Security Officer. Dr. Manson led the effort for Cal Poly Pomona to be designated a National Center of Academic Excellence in Information Assurance Education in 2005, 2008 and 2014. Dr. Manson led the Western Regional Collegiate Cyber Defense Competition from 2018 to 2017 and since 2011 has partnered with schools in CyberPatriot. Dan has been Principal Investigator or co-Principal Investigator on six National Science Foundation grants to support workforce, curriculum and professional development in cyber security, including the current CyberWatch West NSF Cybersecurity Education Regional Center grant. Dan Commissioner for the National Cyber League (NCL).
Tensor Decompositions for Big Multi-aspect Data Analytics
Tensors and tensor decompositions have been very popular and effective tools for analyzing multi-aspect data in a wide variety of fields, ranging from Psychology to Chemometrics, and from Signal Processing to Data Mining and Machine Learning. Using tensors in the era of big data presents us with a rich variety of applications, but also poses great challenges such as the one of scalability and efficiency. In this talk I will first motivate the effectiveness of tensor decompositions as data analytic tools in a variety of exciting, real-world applications. Subsequently, I will discuss recent techniques on tackling the scalability and efficiency challenges by parallelizing and speeding up tensor decompositions, especially for very sparse datasets, including the scenario where the data are continuously updated over time. Finally, I will discuss open problems in unsupervised tensor mining and quality assessment of the results, and present work-in-progress addressing that problem with very encouraging results.
Evangelos (Vagelis) Papalexakis is an Assistant Professor of the CSE Dept. at University of California Riverside. He received his PhD degree at the School of Computer Science at Carnegie Mellon University (CMU). Prior to CMU, he obtained his Diploma and MSc in Electronic & Computer Engineering at the Technical University of Crete, in Greece.
Broadly, his research interests span the fields of Data Mining, Machine Learning, and Signal Processing. His research involves designing scalable algorithms for mining large multi-aspect datasets, with specific emphasis on tensor factorization models, and applying those algorithms to a variety of real world multi-aspect data problems. His work has appeared in KDD, ICDM, SDM, ECML-PKDD, WWW, PAKDD, ICDE, ICASSP, IEEE Transactions of Signal Processing, and ACM TKDD. He has a best student paper award at PAKDD’14 and SDM’16, finalist best papers for SDM'14 and ASONAM'13 and he was a finalist for the Microsoft PhD Fellowship and the Facebook PhD Fellowship. Besides his academic experience, he has industrial research experience working at Microsoft Research Silicon Valley during the summers of 2013 and 2014 and Google Research during the summer of 2015. Finally, his doctoral dissertation received the 2017 SIGKDD Doctoral Dissertation Award (runner up).
University Vision Based Navigation and Tracking with Small UAVs
This talk will describe our current work on vision based autonomous navigation and tracking using small UAVs. We will overview two on-going projects. The first is relative navigation in GPS degraded environments. There are many applications where GPS is either restricted or denied. We have developed an architecture that uses a relative front end to navigate relative to key frames, and then opportunistically uses GPS measurements and SLAM-style loop closures in a back end process to provide global context. We will show some recent flight results that demonstrate robustness to GPS failure and degradation.
The second project that we will discuss is robust tracking of multiple ground based targets from an airborne platform. We will present a new multiple target tracking algorithm that is based on the random sample consensus (RANSAC) algorithm that is widely used in computer vision. A recursive version of the RANSAC algorithm will be discussed, and its extension to tracking multiple dynamic objects will be explained. The performance of R-RANSAC will be compared to state of the art target tracking algorithms in the context of problems that are relevant to UAV applications.
Randal W. Beard received the B.S. degree in electrical engineering from the University of Utah, Salt Lake City in 1991, the M.S. degree in electrical engineering in 1993, the M.S. degree in mathematics in 1994, and the Ph.D. degree in electrical engineering in 1995, all from Rensselaer Polytechnic Institute, Troy, NY. Since 1996, he has been with the Electrical and Computer Engineering Department at Brigham Young University, Provo, UT, where he is currently a professor. In 1997 and 1998, he was a Summer Faculty Fellow at the Jet Propulsion Laboratory, California Institute of Technology, Pasadena, CA. In 2006 and 2007 he was a visiting research fellow at the Air Force Research Laboratory, Munitions Directorate, Eglin AFB, FL. His primary research focus is autonomous control of small air vehicles and multivehicle coordination and control. He is a past associate editor for the IEEE Transactions on Automatic Control, the IEEE Control Systems Magazine, and the Journal of Intelligent and Robotic Systems. He is a fellow of the IEEE, and an associate fellow of AIAA.