1. Tom Erez, University of Washington

    Tuesday, March 19, 2013

    ABSTRACT: Science-fiction robots can perform any task humans do and more. In reality, however, today's articulated robots are disappointingly limited in their motor skills. Current planning and control algorithms cannot provide the robot with the capacity for intelligent motor behavior - instead, control engineers must manually specify the motions of every task. This approach results in jerky motions (popularly stereotyped as "moving like a robot") that cannot cope with unexpected changes.

    I study control methods that automate the job of the controls engineer. I give the robot only a cost function that encodes the task in high-level terms: move forward, remain upright, bring an object, etc. The robot uses a model of itself and its surroundings to optimize its behavior, finding a solution that minimizes the future cost. This optimization-based approach can be applied to different problems, and in every case the robot alone decides how to solve the task. Re-optimizing in real time allows the robot to deal with unexpected deviations from the plan, generating robust and creative behavior that adapts to modeling errors and dynamic environments.

    In this talk, I will present the theoretic and algorithmic aspects needed to control articulated robots using model-based optimization. I will discuss how machine learning can be used to create better controllers and my work on trajectory optimization. Finally, I will describe my vision for the future of model-based optimization in robotics and control. A preview of some of the work discussed in this talk can be seen here: https://dl.dropbox.com/u/57029/MedleyJan13.mp4 [a lower-quality version is also available on YouTube: http://www.youtube.com/watch?v=t4JdSklL8w0]

    BIO: Tom Erez is a Postdoctoral Research Associate in the Computer Science and Engineering department at the University of Washington. He currently leads the controls group in the the UW team for the DARPA Robotics Challenge, building a system for autonomous control of a humanoid robot in a disaster response scenario. His research is concerned with intelligent motor control of robotic and bio-mechanical systems; in particular, he is interested in the interface between machine learning and control theory. His past publications include work on gait optimization, physics simulation, planning under uncertainty, modeling hand-eye coordination, minimax control, and real-time optimization for control. He was awarded the Sackler Scholarship for his research on bio-mechanical models, and his work has been funded by NSF, DARPA, and Willow Garage. Tom received his PhD in Computer Science from Washington University in St. Louis, and his BSc in Mathematics from the Hebrew University in Jerusalem. He also spent three years as a researcher at the University of Amsterdam and the Institute for Scientific Interchange in Turin, Italy, where he studied the application of Statistical Physics models to domains of natural and social sciences.

    Hosted by Dirk Grunwald

    # vimeo.com/62296015 Uploaded 273 Plays 0 Comments
  2. Batya Friedman, University of Washington

    ECCR 265
    Thursday, February 21, 2013

    ABSTRACT: In this colloquium I will provide some reflections: that technology has values; that design matters; and that futures are at stake.

    Tools and technologies are fundamental to the human condition. They do no less than create and structure the conditions in which we live, express ourselves, enact society, and experience what it means to be human. They are also the result of human imagination. Yet, with our limited view, it is not at all obvious how to design tools and technology so that they are more likely to support the actions, relationships, institutions, and experiences that human beings care deeply about.

    In this talk I will explore the question of how to design information and computing technology to be sensitive to human values and concerns. To do so, I will draw from over two decades of design work and theory development. Along the way, I will touch on designing for secure implantable medical devices, for privacy in public, and to support systems of international justice. From there, I will turn to four topics for which cutting edge technology design has provocative implications for human futures: communal intelligence, the human mind, the data cloud, and the planet. Throughout, I will take an interactional stance: that our tools and technologies shape human experience and our very being; and through our experiences and being, we continually re-imagine those very tools and technologies.

    BIO: Batya Friedman is a Professor in the Information School, Adjunct Professor in the Department of Computer Science, and Adjunct Professor in the Department of Human-Centered Design and Engineering at the University of Washington where she directs the Value Sensitive Design Research Lab. Dr. Friedman pioneered value sensitive design (VSD), an approach to account for human values in the design of information systems. First developed in human-computer interaction, VSD has since been used in information management, human-robotic interaction, computer security, civil engineering, applied philosophy, and land use and transportation. Her work has focused on a wide range of values, some include privacy in public, trust, freedom from bias, moral agency, sustainability, safety, calmness, freedom of expression, and human dignity; along with a range of technologies such as web browsers, urban simulation, robotics, open source tools, mobile computing, implantable medical devices, social media, ubiquitous computing and computing infrastructure. Dr. Friedman is currently working on multi-lifespan information system design and on methods for envisioning – imagining new ideas for leveraging information systems to shape our futures. Voices from the Rwanda Tribunal is an early project in this multi-lifespan information system design program. In 2012 Batya Friedman received the ACM-SIGCHI Social Impact Award and the University Faculty Lecturer award at the University of Washington. She received both her B.A. and Ph.D. from the University of California at Berkeley.

    Batya Friedman (http://ischool.uw.edu/people/faculty/batya)
    Value Sensitive Design Research Lab (vsdesign.org)
    Voices from the Rwanda Tribunal (tribunalvoices.org)

    Hosted by Gerhard Fischer

    # vimeo.com/62175522 Uploaded 204 Plays 0 Comments
  3. Janet E. Burge
    Associate Professor of Computer Science and Software Engineering
    Miami University

    Thursday, December 6, 2012

    ABSTRACT: Design rationale has been an active area of research for over 30 years. The reasons for interest are clear—rationale captures the decisions, solutions, and intent during design. Still, rationale capture and use have not made the transition from research to practice. A critical issue is capture—rationale capture is viewed as expensive and tedious. Still, while rationale is not explicitly captured, that does not mean that rationale is not captured at all—decisions are documented in many ways throughout the development process. In this talk I will describe our investigation into techniques to identify and extract rationale from existing documentation. We have been experimenting with different text mining algorithms, while focusing on comparing the results of using different features as the basis of classification. We achieved good results for binary classification of rationale using ensemble-learning methods but have significant room for improvement in classifying rationale as specific argumentation elements.

    BIO: Janet Burge is an Associate Professor in the Miami University Computer Science and Software Engineering department. She received her Ph.D. in Computer Science from Worcester Polytechnic Institute (2005) and performed her undergraduate work at Michigan Technological University (1984). Her research interests include design rationale, software engineering, AI in design, and knowledge elicitation. She is a co-author (with Jack Carroll, Ray McCall, and Ivan Mistrik) of the book “Rationale-Based Software Engineering”. Dr. Burge is a recipient of a NSF CAREER Award for her project “Rationale Capture for High-Assurance Systems”. She has been at Miami University since 2005. Prior to that point, she worked for more than 20 years in industry as a software engineer and research scientist.

    Hosted by Jim Martin

    # vimeo.com/62117502 Uploaded 32 Plays 0 Comments
  4. Kevin Livingston
    University of Colorado School of Medicine
    Computational Bioscience

    Thursday, December 13, 2012

    ABSTRACT: Biomedical researchers face a profound challenge in keeping track and making sense of numerous databases, a growing body of literature, clinical data and records, and data from high-throughput experiments. In this talk I will outline how this is an excellent application domain for AI.

    I will present data motivating the need for semantic integration of diverse sources of biomedical information, and then talk about my research on KaBOB, a knowledge base for integrating curated biomedical databases using community-developed ontologies. KaBOB is currently populated with 19 curated databases and 12 ontologies comprising 8 billion RDF triples. Discussion will include the current status of KaBOB, challenges in building such a large system, and future directions.

    The role of background knowledge, such as the contents of KaBOB, in semantically oriented natural language processing in the biomedical domain will also be discussed. My research demonstrates how background knowledge can be leveraged early in processing (in contrast to the standard pipeline model) to facilitate the understanding of text. Finally a trajectory of NLP research will be outlined establishing a positive feedback loop between knowledge bases and text mining that drives toward a future of more integrated biomedical knowledge.

    BIO: Kevin Livingston is currently a postdoc in the Computational Bioscience Program at the University of Colorado School of Medicine. His research revolves around building intelligent systems that can leverage the large quantities of structured and unstructured data available in the biomedical domain. Current research includes the production of KaBOB, a knowledge base designed to unify curated databases with community consensus ontologies to produce a platform for next-generation intelligent tools for biomedical analysis. This includes tools specifically designed for the bench-scientist as well as text-mining systems for extracting more information from biomedical journal articles or other text-based clinical data.

    Dr. Livingston earned his Ph.D. from the Northwestern University Electrical Engineering and Computer Science Department. His dissertation was in the domain of Natural Language Understanding, specifically leveraging large background knowledge bases to facilitate machine reading. His M.S. work, also at Northwestern, focused on Information Retrieval (IR), most notably work combining structured and unstructured information to retrieve documents. Dr. Livingston has worked in industries of various shapes and sizes, and is an active contributor to open-source software.

    # vimeo.com/62101170 Uploaded 79 Plays 0 Comments
  5. Hassan Ghasemzadeh
    UCLA Wireless Health Institute and San Diego State University

    ECCR 265
    Thursday, March 14, 2013

    ABSTRACT: The rapid expansion of elderly population and increasing costs associated with chronic disease management demand novel technological solutions that shift healthcare services from clinical and hospital settings to a remote and home-bound scenario. Fortunately, the last decade has witnessed rapid advances in several technological domains including electronics, communications, and sensor design leading to the development of new remote health monitoring systems capable of collecting and analyzing varying heterogeneous physiological signals from human subjects. These systems promise to reduce healthcare costs and improve quality of life by reducing the morbidity, mortality, and economic costs associated with hospital re-admissions due to various chronic diseases. The development of effective and sustainable remote health monitoring systems, however, faces a number of challenges regarding their robustness, scalability, power efficiency, and real-time responsiveness.

    This talk presents an end-to-end research methodology for design and development of next generation remote health monitoring platforms, with a particular emphasis on their data analysis and clinical validation. A data-driven system design approach is described to enhance power efficiency and usability of these systems while improving medical outcomes. Results on several ongoing research projects are introduced for optimal sensor selection and placement using wireless medical sensor nodes.

    BIO: Hassan Ghasemzadeh is currently a Research Manager at the UCLA Wireless Health Institute and an Adjunct Professor of Biomedical Informatics at San Diego State University. His research interests lie in different aspects of Embedded System Design including sustainable and green computing, low-power architectures, reconfigurable computing, and system-level optimization. The focus of his current work is on processing platform design, collaborative signal and information processing, power optimization, data analytics, and algorithm design for networked embedded systems with a primary emphasis on applications in healthcare and wellness. His research spans the areas of embedded systems, computer architecture, signal processing, and machine learning, where he has published more than 70 technical papers on the subject including some the earliest works in the field that address fundamental challenges of next generation biomedical systems.

    Hassan is currently leading several research projects funded by NSF, NIH, and industry, is an investigator on several funded proposals, and is a technology lead on many clinical studies. In 2011, he was honored as the Faculty of the Year for his contributions to the Biomedical Informatics program at SDSU. Hassan was the Founding Chair of the Computer Science Department at Azad University, Damavand Branch, Iran, between 2003 and 2006. In the past, he has received several awards including a best poster award from ACM HotMobile 2009, and a best paper award from IEEE RTAS 2011. He received his Ph.D. degree in Computer Engineering from the University of Texas at Dallas in 2010, and spent the academic year 2010-2011 as a Postdoctoral Fellow at the West Health Institute. He received his M.S. degree in Computer Engineering from University of Tehran, Tehran, Iran, in 2001 and his B.S. degree in Computer Engineering from Sharif University of Technology, Tehran, Iran in 1998.

    Hosted by Dirk Grunwald

    # vimeo.com/62095054 Uploaded 315 Plays 0 Comments

Computer Science Colloquia

Be Boulder Anywhere

The University of Colorado Boulder Department of Computer Science holds colloquia throughout the fall and spring semesters. These colloquia, open to the public, are typically held on Thursday afternoons, but sometimes occur at other times as well. Recordings…

+ More

The University of Colorado Boulder Department of Computer Science holds colloquia throughout the fall and spring semesters. These colloquia, open to the public, are typically held on Thursday afternoons, but sometimes occur at other times as well. Recordings are typically posted the following week.

If you would like to receive email notification of upcoming colloquia, please subscribe to our Colloquia Mailing List (http://www.colorado.edu/cs/colloquia/colloquia-mailing-list).

Browse This Channel

Shout Box

Heads up: the shoutbox will be retiring soon. It’s tired of working, and can’t wait to relax. You can still send a message to the channel owner, though!

Channels are a simple, beautiful way to showcase and watch videos. Browse more Channels.