ESE Fall Seminar – “Approximate symmetries in machine learning”

Glandt Forum, Singh Center for Nanotechnology 3205 Walnut Street, Philadelphia, PA, United States

In this talk, we explain different roles that symmetries and approximate symmetries can play in machine learning models. We define approximately equivariant graph neural networks and we show a bias-variance tradeoff when selecting the symmetries to enforce. We explain how to see equivariant functions as gradients of invariant functions, and we show how to use […]

BE Doctoral Dissertation Defense: “Mapping variable host gene expression states to viral infection” (Sam Reffsin)

Smilow Center for Translational Research in SCTR 11-146AB

The Department of Bioengineering at the University of Pennsylvania and Dr. Arjun Raj are pleased to announce the Doctoral Dissertation Defense of Sam Reffsin. Title: Mapping variable host gene expression states to viral infection Date: November 9, 2023 Time: 2:30pm-4:30pm Location: Smilow 11-146AB The public is welcome to attend.

CIS Seminar: “Intrinsic images, lighting and relighting without any labelling”

Wu and Chen Auditorium (Room 101), Levine Hall 3330 Walnut Street, Philadelphia, PA, United States

Intrinsic images are maps of surface properties. A classical problem is to recover an intrinsic image, typically a map of surface lightness, from an image.   The topic has mostly dropped from view, likely for three reasons: training data is mostly synthetic; evaluation is somewhat uncertain; and clear applications for the resulting albedo are missing. […]

CIS Seminar: “Intrinsic images, lighting and relighting without any labeling”

Wu and Chen Auditorium (Room 101), Levine Hall 3330 Walnut Street, Philadelphia, PA, United States

I will show the results of simple experiments that suggest that very good modern depth and normal predictors are strongly sensitive to lighting – if you relight a scene in a reasonable way, the reported depth will change. This is intolerable. To fix this problem, we need to be able to produce many different lightings […]

PRECISE Seminar: Evaluation and calibration of AI models with uncertain ground truth

https://upenn.zoom.us/j/96715197752

For safety, AI systems in health undergo thorough evaluations before deployment, validating their predictions against a ground truth that is assumed certain. However, this is actually not the case and the ground truth may be uncertain. Unfortunately, this is largely ignored in standard evaluation of AI models but can have severe consequences such as overestimating […]

Fall 2023 GRASP on Robotics: Sunil Agrawal, Columbia University, “Rehabilitation Robotics: Improving Everyday Human Functions”

Wu and Chen Auditorium (Room 101), Levine Hall 3330 Walnut Street, Philadelphia, PA, United States

This is a hybrid event with in-person attendance in Wu and Chen and virtual attendance on Zoom. ABSTRACT Neural disorders, old age, and traumatic injuries limit the ability of humans to perform activities of daily living. Robotics can be used to characterize and retrain human neuromuscular responses. Columbia University Robotics and Rehabilitation (ROAR) Laboratory designs […]

PICS Colloquium: “MFEM: Accelerating Efficient Solution of PDEs at Exascale”

https://upenn.zoom.us/j/96715197752

Upcoming exascale architectures require rethinking of the numerical algorithms used in large-scale PDE-based applications. These architectures favor algorithms, such as high-order finite elements, that expose fine-grain parallelism and maximize the ratio of floating point operations to energy intensive data movement. In this talk we present an overview of MFEM , a scalable library for high-order […]

PRECISE Seminar: Wearable Acoustic and Vibration Sensing and Machine Learning for Human Health and Performance

Levine 307 3330 Walnut Street, Philadelphia, PA, United States

Abstract Recent advances in digital health technologies are enabling biomedical researchers to reframe health optimization and disease treatment in a patient-specific, personalized manner. This talk will focus on my group’s research in two areas of relevance to digital health: (1) cardiogenic vibration sensing and analytics; and (2) musculoskeletal sensing with joint acoustic emissions and bioimpedance. […]

MEAM Seminar: “Magnetic Fluid Hyperthermia with Magnetic Iron Oxide Nanoparticles: A Case Study in Multi-disciplinary Translational Biomedical Research”

Wu and Chen Auditorium (Room 101), Levine Hall 3330 Walnut Street, Philadelphia, PA, United States

Magnetic nanoparticles that are responsive to clinically safe magnetic fields offer multi-modal nanomedicine capabilities. To succeed, complexities of physics and engineering must be addressed to match physical and magnetic properties of magnetic nanoparticles with devices used to activate them. This requires thoughtful design and fabrication of both nanoparticles and devices, with appropriate testing in relevant […]

CIS Seminar: “Edge-Weighted Online Bipartite Matching”

Wu and Chen Auditorium (Room 101), Levine Hall 3330 Walnut Street, Philadelphia, PA, United States

Online bipartite matching is one of the most fundamental problems in the online algorithms literature. Karp, Vazirani, and Vazirani (STOC 1990) gave an elegant algorithm for unweighted bipartite matching that achieves an optimal competitive ratio 1-1/e. Aggarwal et al. (SODA 2011) later generalized their algorithm and analysis to the vertex-weighted case. Little is known, however, […]