Learning models of language, action and perception
for human-robot collaboration

Dr. Stefanie Tellex
Department of Computer Science, Brown University

4:00pm Monday, 7 March 2016, ITE325b

Robots can act as a force multiplier for people, whether a robot assisting an astronaut with a repair on the International Space station, a UAV taking flight over our cities, or an autonomous vehicle driving through our streets.  To achieve complex tasks, it is essential for robots to move beyond merely interacting with people and toward collaboration, so that one person can easily and flexibly work with many autonomous robots.  The aim of my research program is to create autonomous robots that collaborate with people to meet their needs by learning decision-theoretic models for communication, action, and perception.  Communication for collaboration requires models of language that map between sentences and aspects of the external world. My work enables a robot to learn compositional models for word meanings that allow a robot to explicitly reason and communicate about its own uncertainty, increasing the speed and accuracy of human-robot communication.  Action for collaboration requires models that match how people think and talk, because people communicate about all aspects of a robot’s behavior, from low-level motion preferences (e.g., “Please fly up a few feet”) to high-level requests (e.g., “Please inspect the building”).  I am creating new methods for learning how to plan in very large, uncertain state-action spaces by using hierarchical abstraction.  Perception for collaboration requires the robot to detect, localize, and manipulate the objects in its environment that are most important to its human collaborator.  I am creating new methods for autonomously acquiring perceptual models in situ so the robot can perceive the objects most relevant to the human’s goals. My unified decision-theoretic framework supports data-driven training and robust, feedback-driven human-robot collaboration.

Stefanie Tellex is an Assistant Professor of Computer Science and Assistant Professor of Engineering at Brown University.  Her group, the Humans To Robots Lab, creates robots that seamlessly collaborate with people to meet their needs using language, gesture, and probabilistic inference, aiming to empower every person with a collaborative robot.  She completed her Ph.D. at the MIT Media Lab in 2010, where she developed models for the meanings of spatial prepositions and motion verbs.  Her postdoctoral work at MIT CSAIL focused on creating robots that understand natural language.  She has published at SIGIR, HRI, RSS, AAAI, IROS, ICAPs and ICMI, winning Best Student Paper at SIGIR and ICMI, Best Paper at RSS, and an award from the CCC Blue Sky Ideas Initiative.  Her awards include being named one of IEEE Spectrum’s AI’s 10 to Watch in 2013, the Richard B. Salomon Faculty Research Award at Brown University, a DARPA Young Faculty Award in 2015, and a 2016 Sloan Research Fellowship.  Her work has been featured in the press on National Public Radio and MIT Technology Review; she was named one of Wired UK’s Women Who Changed Science In 2015 and listed as one of MIT Technology Review’s Ten Breakthrough Technologies in 2016.

Why applications are still draining our batteries, and how we can help

Aaron Schulman, Stanford University

12:00pm Tuesday, 01 March 2016, ITE325b

Application developers lack tools to profile and compare the energy consumption of different software designs. This energy-optimization task is challenging because of unpredictable interactions between the application and increasingly complex power management logic. Yet, having accurate power information would allow application developers to both avoid inefficient designs and discover opportunities for new optimizations.

In this talk, I will show that it is possible to accurately measure system-level power and attribute it to application activities. I will present BattOr, a portable, easy-to-use power monitor that provides developers with a profile of the energy consumption of their designs—without modifications to hardware or software. I will show how Google developers are using BattOr to improve Chrome’s energy efficiency. I will also show how fine-grained understanding of cellular power at different signal strengths enables novel energy optimizations. Finally, I will describe my future plans to attribute system-level power to individual hardware components and to investigate opportunities presented by instrumenting every server in a data center with fine-grained power monitoring.

Aaron Schulman is a Postdoctoral Scholar at Stanford working with Sachin Katti; he earned his Ph.D. in Computer Science from the University of Maryland, where he was advised by Neil Spring. His research interests are in low-power embedded systems, wireless communication, and network measurement. Aaron’s research on the BattOr power monitor has been funded by Google, is being commercialized by his startup Mellow Research, and is becoming Google’s de facto standard tool for measuring the energy consumption of the Chrome web browser. For his dissertation, Aaron provided the first observations of fundamental factors that limit the reliability of the Internet’s critical last-mile infrastructure. His dissertation was selected to receive the the 2013 ACM SIGCOMM Doctoral Dissertation Award.

Learning from High-Dimensional Data via Transformations

Dr. Hossein Mobahi, MIT

12:00pm Monday 29, February 2016, ITE325b

High-dimensional data is ubiquitous in the modern world, arising in images, movies, biomedical measurements, documents, and many other contexts. The “curse of dimensionality” tells us that learning in such regimes is generally intractable. However, practical problems often exhibit special simplifying structures which, when identified and exploited, can render learning in high dimensions tractable. This is a great prospect however, but how to get there in not trivial. In this talk, I will address two challenges associated with high-dimensional learning and discuss my proposed solution.

First, parsimony (sparsity, low rank, etc.) is one of the most prevalent structures in high-dimensional learning applications. However, its presence is often implicit and it reveals itself only after a transformation of the data. Studying the space of such transformations and the associated algorithms for their inference constitute an important class of problems in high-dimensional learning. I will present some of my work in this direction related to image segmentation. I will show how low-rank structures become abundant in images when certain spatial and geometric transformations are considered. This work resulted in a state of the art algorithm for segmentation of natural images.

Second, important scenarios such as deep learning involve high-dimensional nonconvex optimization. Such optimization is generally intractable. However, I show how some properties in the optimization landscape, such as smoothness and stability, can be exploited to transform the objective function to simpler subproblems and allow obtaining reasonable solutions efficiently. The theory is derived by combining the notion of convex envelopes with differential equations. This results in algorithms involving high-dimensional convolution with the Gaussian kernel, which I show has a closed form in many practical scenarios. I will present applications of this work in image alignment, image matching, and deep learning. Furthermore, I will discuss how this theory justifies heuristics currently used in deep learning and suggests new training algorithms that offer a significant speedup.

Hossein Mobahi is a postdoctoral researcher in the Computer Science and Artificial Intelligence Lab at the Massachusetts Institute of Technology. His research interests include machine learning, computer vision, optimization, and especially the intersection of the three. He obtained his PhD from the University of Illinois at Urbana-Champaign in Dec 2012. He is the recipient of Computational Science & Engineering Fellowship, Cognitive Science & AI Award, and Mavis Memorial Scholarship. His recent work on machine learning and optimization have been covered by the MIT news.

The UMBC Cyber Defense Lab presents

Mini-MAC: Raising the Bar for Vehicular Security with a
Lightweight Message Authentication Protocol

Jackson Schmandt, CSEE, UMBC
11:15am-12:30pm Friday, 26 February 2016, ITE 237

We propose Mini-MAC, a new message authentication protocol that works in existing automotive computer networks without delaying any message or increasing network traffic. Deployed in many vehicles, the CAN bus is a low-speed network connecting electronic control units, including those that control critical functionality such as braking and acceleration. The CAN bus is extremely vulnerable to malicious actors with bus access, including wireless access. Traditionally, Message Authentication Codes (MACs) help authenticate the sender of a message, and variants prevent message replay attacks; however, standard MACs are unsuitable for use on the CAN bus because of small payload sizes. Restrictions of the CAN bus, including the need not to delay messages or increase bus traffic, severely limit how well this network can be protected.

Mini-MAC is based on a counter-seeded keyed-Hash MAC (HMAC), augmented with message history and truncated to fit available message space. It does not increase bus traffic and incurs a very small performance penalty relative to the provably secure HMAC. It is the first proposal to combine these two tenets for vehicle networks. The message history feature protects against all transient attackers, even if they know the keys. Though the CAN bus cannot be properly secured against a dedicated attacker, Mini-MAC meaningfully raises the bar of vehicular security, enhancing the safety of drivers and others.

Jackson Schmandt is a MS student in Computer Engineering in the Mobile Pervasive Sensor System Lab. Joint work with Alan Sherman and Nilanjan Banerjee.

Host: Alan T. Sherman, Sorry, you need javascript to view this email address.

Establishment of Trust and Integrity in Modern Supply Chains

Ujjwal Guin, University of Connecticut

11:30 Thursday, 25 February 2016, ITE325b

With the advent of globalization and resulting horizontal integration, modern supply chain becomes extremely complex and requires immediate solutions for eliminating counterfeit integrated circuits (ICs), which pose a serious threat to the safety and security of our day-to-day lives. The reliability of such ICs could be questionable as they may have many defects and might not go through as much of a rigorous test process as their authentic counterparts. An adversary can also create a backdoor to bypass the security modules in these ICs. In this research, I have systematically addressed the aforementioned issues by risk analysis and assessment of test methods, and by proposing different Design-for-Anti-Counterfeit (DfAC) measures. As a part of risk analysis, I have developed taxonomies for counterfeit IC types, counterfeit defects, and test methods. Based on these taxonomies, I have introduced novel test metrics and developed a comprehensive framework for assessing a set of test methods to maximize test coverage. In the DfAC domain, I have proposed a suite of solutions to detect counterfeit ICs without performing conventional tests. A set of lightweight negative-bias temperature instability (NBTI)-aware ring oscillators have been developed for combating die and IC recycling. In addition, I have developed a comprehensive solution for preventing intellectual property piracy and IC overproduction by assuring forward trust between all entities involved in the system-on-chip design and fabrication process.

Ujjwal Guin is a PhD candidate at the Electrical and Computer Engineering department of University of Connecticut, where he has been working with Dr. Mark M. Tehranipoor. His current research interests include Hardware Security and Trust, Supply Chain Security, Cybersecurity, and VLSI Design and Test. He has developed several on-chip structures and techniques to improve the security, trustworthiness, and reliability of integrated circuits. He has co-authored a book entitled “Counterfeit Integrated Circuits – Detection and Avoidance”. He has published several journal articles and refereed conference papers. He received Best Student Paper Award from the IEEE North Atlantic Test Workshop (NATW’2013). He is an active participant in the SAE International’s G-19A Test Laboratory Standards Development Committee. Mr. Guin received his B.E. degree from the Department of Electronics and Telecommunication Engineering of Bengal Engineering and Science University, Howrah, India in 2004 and the M.Sc. degree from the Department of Electrical and Computer Engineering of Temple University, Philadelphia, PA, USA in 2010.

Host: Chintan Patel

Leveraging Human Insights into
Problem Structure for Scientific Discovery

Ronan Le Bras, Cornell University

12:00pm 1:00pm Tuesday, 23 February 2016, ITE325b, UMBC

Most problems, from theoretical problems in combinatorics to real-world applications, comprise hidden structural properties not directly captured by the problem definition. A key to the recent progress in automated reasoning and combinatorial optimization has been to automatically uncover and exploit this hidden problem structure, resulting in a dramatic increase in the scale and complexity of the problems within our reach. The most complex tasks, however, still require human abilities and ingenuity. In this talk, I will show how we can leverage human insights to effectively complement and dramatically boost state-of-the-art optimization techniques. I will demonstrate the effectiveness of the approach with a series of scientific discoveries, from experimental designs to materials discovery.

Ronan Le Bras is a Ph.D. candidate in computer science at Cornell University. He received his M.S. and B.S. from Ecole Polytechnique Montreal in computer engineering and in software engineering. His research interests include computational methods for large-scale combinatorial optimization, reasoning, learning and human computation. His work is motivated by a range of applications, especially in the emerging field of computational sustainability. It has led to a series of scientific discoveries in areas such as graph theory, combinatorics, and discrepancy theory as well as materials science, experimental design and conservation biology. His work appears in the proceedings of AAAI, IJCAI, HCOMP, SAT, CP and VLDB.

Host:  Tim Finin, Sorry, you need javascript to view this email address.

From Forensics to Security: Securing Complex
Systems through Data-driven Investigation

Dr. Robert Walls
Pennsylvania State University

1:00pm Friday, 19 February 2016, ITE 325b, UMBC

The cornerstone of modern security is understanding when and how systems are abused and exploited. Gathering such knowledge is essential as decades of experience demonstrate the infeasibility of building perfectly secure systems. Yet, the systems with the greatest need of securing—such as those underpinning critical Internet services—are often the most difficult to study.

In this talk, I will focus on my research efforts in digital forensics and security to study the abuse of complex and inter-connected systems. My work has focused on multiple aspects of this endeavor, including the analysis of partially structured data, the use of semantic relationships and investigator feedback to identify relevant information, and the transition of research results into practical tools and techniques.

Robert Walls is a Postdoctoral Scholar in the Department of Computer Science and Electrical Engineering at The Pennsylvania State University. His research interests include systems security and digital forensics. He is currently studying the abuse of Internet infrastructure, including advertising networks and the Domain Name System (DNS). Previously, he worked with law enforcement to develop novel forensic techniques for investigating crimes. He received his Ph.D. in Computer Science from the University of Massachusetts Amherst in 2014. He is also a recipient of the Yahoo! Key Scientific Challenges Award.

Host: Tim Finin, Sorry, you need javascript to view this email address.

From Forensics to Security: Securing Complex
Systems through Data-driven Investigation

Dr. Robert Walls
Pennsylvania State University

1:00pm Friday, 19 February 2016, ITE 325b, UMBC

The cornerstone of modern security is understanding when and how systems are abused and exploited. Gathering such knowledge is essential as decades of experience demonstrate the infeasibility of building perfectly secure systems. Yet, the systems with the greatest need of securing—such as those underpinning critical Internet services—are often the most difficult to study.

In this talk, I will focus on my research efforts in digital forensics and security to study the abuse of complex and inter-connected systems. My work has focused on multiple aspects of this endeavor, including the analysis of partially structured data, the use of semantic relationships and investigator feedback to identify relevant information, and the transition of research results into practical tools and techniques.

Robert Walls is a Postdoctoral Scholar in the Department of Computer Science and Electrical Engineering at The Pennsylvania State University. His research interests include systems security and digital forensics. He is currently studying the abuse of Internet infrastructure, including advertising networks and the Domain Name System (DNS). Previously, he worked with law enforcement to develop novel forensic techniques for investigating crimes. He received his Ph.D. in Computer Science from the University of Massachusetts Amherst in 2014. He is also a recipient of the Yahoo! Key Scientific Challenges Award.

Host: Tim Finin, Sorry, you need javascript to view this email address.

Big Data/Data Science Programs at NSF

Chaitan Baru
Senior Advisor for Data Science, NSF CISE Directorate
10-11:00am Friday 12 February 2016, ITE 459, UMBC

This talk will provide an overview of current programs and activities related to Big Data and Data Science at NSF, and also highlight NSF’s inter-agency engagements in this topic area. The talk will also discuss future directions for Data Science research, education, and infrastructure. Considering that Data Science is a rapidly emerging, evolving field and discipline, ample time will be provided for Q&A and discussions about where the field ought to be going, given what we know today.

Dr. Chaitan Baru is currently a senior advisor for data science in the Computer and Information Science and Engineering Directorate at the National Science Foundation. He is a Distinguished Scientist and Associate Director of Data Initiatives at the San Diego Supercomputer Center (SDSC), UC San Diego where he works on applied and applications-oriented research problems related to data management and data analytics.

Dr. Baru has participated in a number of “data cyberinfrastructure” initiatives, including as Principal Investigator of the OpenTopography project; Cyberinfrastructure Lead, Tropical Ecology, Assessment and Monitoring network; Co-Investigator of the Cyberinfrastructure for Comparative Effectiveness Research project; Member of the founding Senior Management Team of the National Ecologial Observatory Network and Co-PI of the NEON Cyberinfrastructure Testbed; Co-PI of the CUAHSI Hydrologic Information Systems; Director, NEES Cyberinfrastructure Center; PI/Project Director, Geosciences Network; and member of the How Much Information? project.

Baru leads the Advanced Cyberinfrastructure Development Group at SDSC and is also Director of the Center for Large-scale Data Systems research. Prior to joining SDSC in 1996, Baru was at IBM, where he led one of the development teams for DB2 Parallel Edition Version 1 and at the University of Michigan, where he served on the faculty of the EECS Department. He received his B.Tech in Electronics Engineering from the Indian Institute of Technology, Madras, and M.E. and Ph.D. in Electrical Engineering from the University of Florida, Gainesville.

Big Data/Data Science Programs at NSF

Chaitan Baru
Senior Advisor for Data Science, NSF CISE Directorate
10-11:00am Friday 12 February 2016, ITE 459, UMBC

This talk will provide an overview of current programs and activities related to Big Data and Data Science at NSF, and also highlight NSF’s inter-agency engagements in this topic area. The talk will also discuss future directions for Data Science research, education, and infrastructure. Considering that Data Science is a rapidly emerging, evolving field and discipline, ample time will be provided for Q&A and discussions about where the field ought to be going, given what we know today.

Dr. Chaitan Baru is currently a senior advisor for data science in the Computer and Information Science and Engineering Directorate at the National Science Foundation. He is a Distinguished Scientist and Associate Director of Data Initiatives at the San Diego Supercomputer Center (SDSC), UC San Diego where he works on applied and applications-oriented research problems related to data management and data analytics.

Dr. Baru has participated in a number of “data cyberinfrastructure” initiatives, including as Principal Investigator of the OpenTopography project; Cyberinfrastructure Lead, Tropical Ecology, Assessment and Monitoring network; Co-Investigator of the Cyberinfrastructure for Comparative Effectiveness Research project; Member of the founding Senior Management Team of the National Ecologial Observatory Network and Co-PI of the NEON Cyberinfrastructure Testbed; Co-PI of the CUAHSI Hydrologic Information Systems; Director, NEES Cyberinfrastructure Center; PI/Project Director, Geosciences Network; and member of the How Much Information? project.

Baru leads the Advanced Cyberinfrastructure Development Group at SDSC and is also Director of the Center for Large-scale Data Systems research. Prior to joining SDSC in 1996, Baru was at IBM, where he led one of the development teams for DB2 Parallel Edition Version 1 and at the University of Michigan, where he served on the faculty of the EECS Department. He received his B.Tech in Electronics Engineering from the Indian Institute of Technology, Madras, and M.E. and Ph.D. in Electrical Engineering from the University of Florida, Gainesville.