May 2022 - Ai - Engineering Mailing Lists

[CoRIS-List] OSU Robotics Seminar 06/03: Edward Wang, "Healthcare in the Age of Information Technology"
by Ross L. Hatton 31 May '22

31 May '22

Hi All, Our final OSU Robotics seminar of the term will be presented by Edward Wang from the University of California, San Diego, on "Healthcare in the Age of Information Technology: Opportunities and Real-world Challenges". The seminar will be from 10-11am, followed by an 11-11:30 student-only Q&A session. The seminar will be an *in person* event, simulcast over Zoom, and will be immediately followed by a half-hour students-only Q&A session with the speaker. June 3, 10am LINC 268 https://oregonstate.zoom.us/j/93908195212?pwd=cEdoQVdac0JxMUpOSS9xVzZjVG5xU… <https://oregonstate.zoom.us/j/93908195212?pwd=cEdoQVdac0JxMUpOSS9xVzZjVG5xU…> ----------------- Seminar Title: Healthcare in the Age of Information Technology: Opportunities and Real-world Challenges Abstract: With the ubiquity of digital technologies that is seeping into every fabric of our lives, we are presented with an opportunity to harness the economy of scale that is driving down the cost of distributing a wide array of sensors that can be repurposed and reprogrammed. This effect is particularly impactful for the way healthcare is and can be designed, not only as an opportunity to completely change the way we deliver care, but also the potential issues it may cause. Smartphones stand to become the Tricorder that will deliver an ever-expanding library of health metrics through software applications. The induction of wearable devices like the Fitbit and the Apple Watch is introducing passive monitoring of physiological signals that once was exclusive to ICUs (not even primary care) at unprecedented scales. Even something as “mundane” today as a video call, is creating an entire new paradigm of telemedicine. In this talk, I will share with you late breaking work that my group, the DigiHealth Lab is doing around discovering new digital biomarkers for Alzheimer’s screening, improving breastfeeding efficacy for mothers, making blood pressure monitoring as continuous, and passively enabling mass monitoring of individuals for upper-respiratory infections with wearable sensors. It is in this context of developing and designing these technologies beyond the theory and simulation, however, where we are faced with the real-world challenges of bringing such a distributed and federated healthcare system together. I hope to use this opportunity to not only share with you the impact that digital health technologies will make, but also the difficulties and challenges to make such technologies work safely, inclusively, and ultimately better. Bio: Dr. Edward Jay Wang is an Assistant Professor of Electrical and Computer Engineering & The Design Lab at UC San Diego, where he directs the DigiHealth Lab. He earned his Ph.D. from the University of Washington under Dr. Shwetak Patel and his B.S. from Harvey Mudd College His research work explores practical solutions to address real-world medical needs drawn from collaborations with clinicians and world health organizations, but solved in new, creative ways that leverage state-of-the-art applied machine learning, embedded systems, and mobile sensors. His work is currently being funded by the NIH, National Institute of Aging, and UC San Diego Galvanizing Engineering in Medicine (GEM). He has been the recipient of the Google Faculty Research Scholar Award, NSF Graduate Fellowship Award, the ARCS Foundation Fellowship, and 5 publication paper awards. He has published in top-tier venues in Computer Science and Biology, including ACM UbiComp, CHI, UIST, and Nature Scientific Reports. He is currently a member of the UCSD Center for Wireless & Populational Health Systems and a Board of Director of the Center for Mental Health Technologies. =========== Ross L. Hatton Associate Professor, Robotics and Mechanical Engineering Collaborative Robotics and Intelligent Systems Institute Oregon State University coris.oregonstate.edu <http://coris.oregonstate.edu/> research.engr.oregonstate.edu/lram/ <http://research.engr.oregonstate.edu/lram/> rosslhatton.com <http://rosslhatton.com/> ross.hatton(a)oregonstate.edu

1 0

AI seminar: Jun 1, 2022
by Mangannavar, Rajesh Devaraddi 31 May '22

31 May '22

Dear all, Our next AI seminar on *"Enabling Humans and Robots to Predict the Other’s Behavior from Small Datasets" *by Vaibhav Unhelkar is scheduled to be on June 1st (tomorrow), 1-2 PM PST (Add to google calendar <https://calendar.google.com/event?action=TEMPLATE&tmeid=YXExYTZuY2NiZXRhbHJ…> ). It will be followed by a 30-minute Q&A session by the graduate students. Zoom Link: https://oregonstate.zoom.us/j/93591935144?pwd=YjZaSjBYS0NmNUtjQzBEdzhPeDZ5U… *Enabling Humans and Robots to Predict the Other’s Behavior from Small Datasets* Vaibhav Unhelkar Assistant Professor of Computer Science Rice University *Abstract:* We are steadily moving towards a future where humans work with robotic assistants, teammates, and even trainers. Towards realizing this future and mitigating its adverse side effects, I will share two techniques that together enable humans and robots to predict the other’s task-oriented behavior. First, I will present AI Teacher: an interactive machine teaching framework to assist humans in acquiring mental models of robots. By building upon human’s natural ability to model others (Theory of Mind), the AI Teacher framework reduces the number of interactions it takes for humans to arrive at predictive models of robot behavior. Second, I will discuss BTIL, an imitation learning approach for enabling robots to arrive at predictive models of humans’ collaborative behavior. Discussions of both these techniques will highlight the need as well as solutions for sample-efficient learning in settings of human-robot collaboration. *Speaker Bio:* Vaibhav Unhelkar is an Assistant Professor of Computer Science at Rice University, where he leads a research group in the emerging area of Human-Centered AI. Ongoing research in his group includes development of algorithms and systems that enable “robots to work with humans” and “humans to become informed users of robots.” Unhelkar received his doctorate in Autonomous Systems at MIT (2020) and completed his undergraduate education at IIT Bombay (2012). He serves as an Associate Editor for IEEE Robotics and Automation Letters and is the recipient of JPMC AI Early Career Researcher Award and AAMAS 2022 Best PC Member Award. Before joining Rice, Unhelkar worked as a robotics researcher at X, the Moonshot Factory (formerly, Google X). *Please watch this space for future AI Seminars :* * https://eecs.oregonstate.edu/ai-events <https://eecs.oregonstate.edu/ai-events>* Rajesh Mangannavar, Graduate Student Oregon State University ---- AI Seminar Important Reminders: -> For graduate students in the AI program, attendance is strongly encouraged.

1 0

[CoRIS-List] Capprin Bass' Masters Defense: June 8th 10:00AM
by Bass, Capprin James 30 May '22

30 May '22

Hello everyone, I will be defending my masters thesis next Wednesday, June 8th at 10:00AM. You are all welcome to attend; details are below. *When: *Wednesday, June 8th at 10:00AM PDT *Where: *Rogers 226, or simulcast over Zoom *Title: *Geometric Optimization Methods for Mobile Systems *Abstract:* When studying robot systems, it is common to ask about optimal approaches to accomplish a given task. In the context of mobile systems, particularly biomimetic systems, optimization tasks are closely related to the relevant dynamics of locomotion. In this thesis, building on prior work from the geometric mechanics community, we introduce several methods for optimization in the context of mobile systems. Each topic is covered in a separate manuscript: in the first manuscript, we investigate how error accrues when using second order displacement approximations for planar mobile systems, and how coordinate optimization reduces error by accounting for higher order error effects. In the second manuscript, we extend planar coordinate optimization to the group of 3D rotations, clarifying methods presented in prior work. Contributions introduced here further reduce error inherent to displacement approximations. In the third and final manuscript, we use recent robot gait optimization methods to perform dimensionality reduction on robot shape spaces, respecting useful dynamics. The resulting 2D shape spaces have useful topological and geometric properties, and could act as a building block for more general robot dimensionality reduction. Finally, the conclusion summarizes the shared themes of the included papers, and discusses in general the potential of geometric mechanics in future robotics work. *Advisor: *Dr. Ross L. Hatton *Committee: *Dr. Ross L. Hatton, Dr. Joseph Davidson, Dr. Ren Guo, Dr. Barbara Simpson *Zoom Meeting:* Capprin Bass is inviting you to a scheduled Zoom meeting. Topic: Capprin Bass' Masters Thesis Defense Time: Jun 8, 2022 10:00 AM Pacific Time (US and Canada) Join Zoom Meeting https://oregonstate.zoom.us/j/94321608275?pwd=NnFOUHkyREhyL1R0YmdBTm9RcjFxZ… Password: 255135 Phone Dial-In Information +1 971 247 1195 US (Portland) +1 253 215 8782 US (Tacoma) +1 301 715 8592 US (Washington DC) Meeting ID: 943 2160 8275 Join by Polycom/Cisco/Other Room System 94321608275(a)zoomcrc.com Thanks all, Capprin Bass

1 0

AI seminar: May 25, 2022
by Mangannavar, Rajesh Devaraddi 27 May '22

27 May '22

Dear all, Our next AI seminar on *"Toward Addressing Evaluation and Explanation Challenges in Scientific ML Applications" *by Shusen Liu is scheduled to be on May 25th, 1-2 PM PST (Add to google calendar <https://calendar.google.com/event?action=TEMPLATE&tmeid=YXExYTZuY2NiZXRhbHJ…> ). It will be followed by a 30-minute Q&A session by the graduate students. Zoom Link: https://oregonstate.zoom.us/j/93591935144?pwd=YjZaSjBYS0NmNUtjQzBEdzhPeDZ5U… *Toward Addressing Evaluation and Explanation Challenges in Scientific ML Applications* Shusen Liu Research Scientist Machine Intelligence Group Lawrence Livermore National Laboratory *Abstract:* Although the influence of deep learning in scientific domains is unmistakable, there are still fundamental barriers to utilizing these complex models for scientific discovery due in part to our inability to directly translate their predictive capabilities into scientific understanding. The root of the problem is twofold: 1) the challenge to evaluate the model in the context of the application; 2) the difficulties of reasoning about such models in terms that domain scientists can easily understand for knowledge extraction. This talk will provide a closer look at these unique challenges associated with applying deep learning to scientific applications. And cover some of our works for addressing the evaluation and explanation challenges in Scientific ML. Specifically, we will show how topological data analysis plays a crucial role in evaluating deep surrogate models for fusion science, and how deep generative models allow us to explore hypothetical materials and obtain actionable explanations that lead to improved material performance. *Speaker Bio:* Shusen Liu is a research scientist with the Machine Intelligence Group at the Lawrence Livermore National Laboratory (LLNL). His interests include fundamental research in explainable AI and high-dimensional data visualization, as well as their impact on scientific applications for advancing domain understanding. He received a Ph.D.in computing from the University of Utah in 2017. *Please watch this space for future AI Seminars :* * https://eecs.oregonstate.edu/ai-events <https://eecs.oregonstate.edu/ai-events>* Rajesh Mangannavar, Graduate Student Oregon State University ---- AI Seminar Important Reminders: -> For graduate students in the AI program, attendance is strongly encouraged.

2 1

AI seminar: Jun 1, 2022
by Mangannavar, Rajesh Devaraddi 26 May '22

26 May '22

Dear all, Our next AI seminar on *"Enabling Humans and Robots to Predict the Other’s Behavior from Small Datasets" *by Vaibhav Unhelkar is scheduled to be on June 1st, 1-2 PM PST (Add to google calendar <https://calendar.google.com/event?action=TEMPLATE&tmeid=YXExYTZuY2NiZXRhbHJ…> ). It will be followed by a 30-minute Q&A session by the graduate students. Zoom Link: https://oregonstate.zoom.us/j/93591935144?pwd=YjZaSjBYS0NmNUtjQzBEdzhPeDZ5U… *Enabling Humans and Robots to Predict the Other’s Behavior from Small Datasets* Vaibhav Unhelkar Assistant Professor of Computer Science Rice University *Abstract:* We are steadily moving towards a future where humans work with robotic assistants, teammates, and even trainers. Towards realizing this future and mitigating its adverse side effects, I will share two techniques that together enable humans and robots to predict the other’s task-oriented behavior. First, I will present AI Teacher: an interactive machine teaching framework to assist humans in acquiring mental models of robots. By building upon human’s natural ability to model others (Theory of Mind), the AI Teacher framework reduces the number of interactions it takes for humans to arrive at predictive models of robot behavior. Second, I will discuss BTIL, an imitation learning approach for enabling robots to arrive at predictive models of humans’ collaborative behavior. Discussions of both these techniques will highlight the need as well as solutions for sample-efficient learning in settings of human-robot collaboration. *Speaker Bio:* Vaibhav Unhelkar is an Assistant Professor of Computer Science at Rice University, where he leads a research group in the emerging area of Human-Centered AI. Ongoing research in his group includes development of algorithms and systems that enable “robots to work with humans” and “humans to become informed users of robots.” Unhelkar received his doctorate in Autonomous Systems at MIT (2020) and completed his undergraduate education at IIT Bombay (2012). He serves as an Associate Editor for IEEE Robotics and Automation Letters and is the recipient of JPMC AI Early Career Researcher Award and AAMAS 2022 Best PC Member Award. Before joining Rice, Unhelkar worked as a robotics researcher at X, the Moonshot Factory (formerly, Google X). *Please watch this space for future AI Seminars :* * https://eecs.oregonstate.edu/ai-events <https://eecs.oregonstate.edu/ai-events>* Rajesh Mangannavar, Graduate Student Oregon State University ---- AI Seminar Important Reminders: -> For graduate students in the AI program, attendance is strongly encouraged.

1 0

AI Alignment Reading Group
by Pope, Quintin 26 May '22

26 May '22

Hello everyone, We'll be meeting at 2 PM PST on Friday to discuss the paper The Boltzmann Policy Distribution: Accounting for Systematic Suboptimality in Human Models <https://arxiv.org/abs/2204.10759>. Models of human behavior for prediction and collaboration tend to fall into two categories: ones that learn from large amounts of data via imitation learning, and ones that assume human behavior to be noisily-optimal for some reward function. The former are very useful, but only when it is possible to gather a lot of human data in the target environment and distribution. The advantage of the latter type, which includes Boltzmann rationality, is the ability to make accurate predictions in new environments without extensive data when humans are actually close to optimal. However, these models fail when humans exhibit systematic suboptimality, i.e. when their deviations from optimal behavior are not independent, but instead consistent over time. Our key insight is that systematic suboptimality can be modeled by predicting policies, which couple action choices over time, instead of trajectories. We introduce the Boltzmann policy distribution (BPD), which serves as a prior over human policies and adapts via Bayesian inference to capture systematic deviations by observing human actions during a single episode. The BPD is difficult to compute and represent because policies lie in a high-dimensional continuous space, but we leverage tools from generative and sequence models to enable efficient sampling and inference. We show that the BPD enables prediction of human behavior and human-AI collaboration equally as well as imitation learning-based human models while using far less data. Join Zoom Meeting https://oregonstate.zoom.us/j/95843260079?pwd=TzZTN0xPaFZrazRGTElud0J1cnJLU… Password: 961594 Phone Dial-In Information +1 971 247 1195 US (Portland) +1 253 215 8782 US (Tacoma) +1 301 715 8592 US (Washington DC) Meeting ID: 958 4326 0079 All the best, Quintin Pope

1 0

AI seminar: May 25, 2022
by Mangannavar, Rajesh Devaraddi 25 May '22

25 May '22

Dear all, Our next AI seminar on *"Toward Addressing Evaluation and Explanation Challenges in Scientific ML Applications" *by Shusen Liu is scheduled to be on May 25th (tomorrow), 1-2 PM PST (Add to google calendar <https://calendar.google.com/event?action=TEMPLATE&tmeid=YXExYTZuY2NiZXRhbHJ…> ). It will be followed by a 30-minute Q&A session by the graduate students. Zoom Link: https://oregonstate.zoom.us/j/93591935144?pwd=YjZaSjBYS0NmNUtjQzBEdzhPeDZ5U… *Toward Addressing Evaluation and Explanation Challenges in Scientific ML Applications* Shusen Liu Research Scientist Machine Intelligence Group Lawrence Livermore National Laboratory *Abstract:* Although the influence of deep learning in scientific domains is unmistakable, there are still fundamental barriers to utilizing these complex models for scientific discovery due in part to our inability to directly translate their predictive capabilities into scientific understanding. The root of the problem is twofold: 1) the challenge to evaluate the model in the context of the application; 2) the difficulties of reasoning about such models in terms that domain scientists can easily understand for knowledge extraction. This talk will provide a closer look at these unique challenges associated with applying deep learning to scientific applications. And cover some of our works for addressing the evaluation and explanation challenges in Scientific ML. Specifically, we will show how topological data analysis plays a crucial role in evaluating deep surrogate models for fusion science, and how deep generative models allow us to explore hypothetical materials and obtain actionable explanations that lead to improved material performance. *Speaker Bio:* Shusen Liu is a research scientist with the Machine Intelligence Group at the Lawrence Livermore National Laboratory (LLNL). His interests include fundamental research in explainable AI and high-dimensional data visualization, as well as their impact on scientific applications for advancing domain understanding. He received a Ph.D. in <http://ph.d.in/> computing from the University of Utah in 2017. *Please watch this space for future AI Seminars :* * https://eecs.oregonstate.edu/ai-events <https://eecs.oregonstate.edu/ai-events>* Rajesh Mangannavar, Graduate Student Oregon State University ---- AI Seminar Important Reminders: -> For graduate students in the AI program, attendance is strongly encouraged.

1 0

Alignment Reading Group Meeting Canceled
by Pope, Quintin 20 May '22

20 May '22

Hello everyone, I'm canceling our meeting today. I've been busy with other projects and haven't had time to prepare. If you're interested, I'd been intending to discuss The Boltzmann Policy Distribution: Accounting for Systematic Suboptimality in Human Models <https://arxiv.org/abs/2204.10759>. Models of human behavior for prediction and collaboration tend to fall into two categories: ones that learn from large amounts of data via imitation learning, and ones that assume human behavior to be noisily-optimal for some reward function. The former are very useful, but only when it is possible to gather a lot of human data in the target environment and distribution. The advantage of the latter type, which includes Boltzmann rationality, is the ability to make accurate predictions in new environments without extensive data when humans are actually close to optimal. However, these models fail when humans exhibit systematic suboptimality, i.e. when their deviations from optimal behavior are not independent, but instead consistent over time. Our key insight is that systematic suboptimality can be modeled by predicting policies, which couple action choices over time, instead of trajectories. We introduce the Boltzmann policy distribution (BPD), which serves as a prior over human policies and adapts via Bayesian inference to capture systematic deviations by observing human actions during a single episode. The BPD is difficult to compute and represent because policies lie in a high-dimensional continuous space, but we leverage tools from generative and sequence models to enable efficient sampling and inference. We show that the BPD enables prediction of human behavior and human-AI collaboration equally as well as imitation learning-based human models while using far less data. All the best, Quintin Pope

1 0

[CoRIS-List] Reminder: Today: OSU Robotics Seminar 05/20: Reid Simmons, "Agents that Learn and Teach"
by Ross L. Hatton 20 May '22

20 May '22

Hi All, As a reminder today's OSU Robotics seminar will be presented by Reid Simmons from the Carnegie Mellon University, on "Agents that Learn and Teach". The seminar will be from 10-11am, followed by an 11-11:30 student-only Q&A session. The seminar will be an *in person* event, simulcast over Zoom, and will be immediately followed by a half-hour students-only Q&A session with the speaker. May 20, 10am LINC 268 https://oregonstate.zoom.us/j/93908195212?pwd=cEdoQVdac0JxMUpOSS9xVzZjVG5xU… <https://oregonstate.zoom.us/j/93908195212?pwd=cEdoQVdac0JxMUpOSS9xVzZjVG5xU…> ----------------- Seminar Title: Agents that Learn and Teach Abstract:This talk will present recent work by my students who are investigating how agents can learn from people and teach them effectively and efficiently. In terms of learning, we have explored having agents use multiple modes of interaction, such as providing demonstrations and indicating preferences, to more effectively learn personal preferences. On the teaching side, we have explored having agents use counterfactual demonstrations, based on mental models of the learner, to efficiently scaffold learning of the agent's policies. We have also explored how providing non-verbal affective feedback can improve human learning, even if the feedback does not provide any information relevant to the task at hand. I'll also speculate on how this research can be used in assisting the elderly and their caregivers, as part of the new NSF AI-CARING Institute, of which CMU and OSU are both participants. Bio: Reid Simmons is a Research Professor in Robotics and Computer Science at Carnegie Mellon University. He is also the director of the first-in-the-country undergraduate major in Artificial Intelligence. Dr. Simmons earned his PhD from MIT in 1988 in the field of Artificial Intelligence. Since coming to CMU in 1988, he has focused on developing self-reliant robots that can autonomously operate over extended periods of time in unknown, unstructured environments. Specific research interests include human-robot social interaction, especially non-verbal communication through affect, proxemics, motion, and gesture, task planning under uncertainty, execution monitoring and failure recovery, and coordination of multiple heterogeneous robots. He also served as a Program Director at the National Science Foundation, where he oversaw the National Robotics Initiative and Smart and Autonomous Systems programs. =========== Ross L. Hatton Associate Professor, Robotics and Mechanical Engineering Collaborative Robotics and Intelligent Systems Institute Oregon State University coris.oregonstate.edu <http://coris.oregonstate.edu/> research.engr.oregonstate.edu/lram/ <http://research.engr.oregonstate.edu/lram/> rosslhatton.com <http://rosslhatton.com/> ross.hatton(a)oregonstate.edu <mailto:ross.hatton@oregonstate.edu>

1 0

AI seminar: May 18, 2022
by Mangannavar, Rajesh Devaraddi 17 May '22

17 May '22

Dear all, Our next AI seminar on *"Few-Shot Object Segmentation" *by professor Sinisa Todorovic is scheduled to be on May 18th(Tomorrow), 1-2 PM PST (Add to google calendar <https://calendar.google.com/event?action=TEMPLATE&tmeid=YXExYTZuY2NiZXRhbHJ…> ). It will be followed by a 30-minute Q&A session by the graduate students. Zoom Link: https://oregonstate.zoom.us/j/93591935144?pwd=YjZaSjBYS0NmNUtjQzBEdzhPeDZ5U… *Few-Shot Object Segmentation* Sinisa Todorovic Professor Computer Science Oregon State University *Abstract:* This talk will be about few-shot instance segmentation in images -- a basic computer vision problem arising in many applications with access to only a few examples of target object classes due to, e.g., their rarity. Our main research accomplishments in this area will be presented, including: explicit modeling and discovery of latent object parts shared across object classes; data uncertainty map estimation for each instance segmentation and data uncertainty based regularization of our few-shot learning; and model uncertainty estimation with an efficient approximation based on the probit function. Our contributions produce statistically significant performance gains over the state of the art on the benchmark COCO dataset. *Speaker Bio:* Sinisa Todorovic is a Professor in the School of Electrical Engineering and Computer Science at Oregon State University (OSU). He joined OSU in 2008, after three years of conducting postdoctoral research in the Beckman Institute at University of Illinois Urbana-Champaign (UIUC). He received his Ph.D. degree in electrical and computer engineering at University of Florida. Todorovic conducts research in computer vision with focus on object and human-activity recognition. He has served as a co-Program Chair of IEEE International Conference on Automatic Face and Gesture Recognition FG 2015, co-organized a number of tutorials and workshops on stochastic image grammars at top vision conferences, and currently serves as Editor-in-Chief of the Image and Vision Computing journal. His research has been funded by a number of federal agencies, including NSF and DARPA, as well as the IT industry. He received Jack Neubauer Best Paper Award from IEEE Transactions on Vehicular Technology in 2014, and the Oregon State College of Engineering Research Collaboration Award in 2016. This talk will be followed by a talk on the topic " *Toward Addressing Evaluation and Explanation Challenges in Scientific ML Applications*" by Shusen Liu on 25th May (Wednesday) 1-2 PM, 2022 *Please watch this space for future AI Seminars :* * https://eecs.oregonstate.edu/ai-events <https://eecs.oregonstate.edu/ai-events>* Rajesh Mangannavar, Graduate Student Oregon State University ---- AI Seminar Important Reminders: -> For graduate students in the AI program, attendance is strongly encouraged.

1 0