BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Penn Engineering Events - ECPv6.15.18//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Penn Engineering Events
X-ORIGINAL-URL:https://seasevents.nmsdev7.com
X-WR-CALDESC:Events for Penn Engineering Events
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20230312T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20231105T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20240310T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20241103T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20250309T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20251102T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20240118T153000
DTEND;TZID=America/New_York:20240118T163000
DTSTAMP:20260404T085842
CREATED:20240108T170619Z
LAST-MODIFIED:20240108T170619Z
UID:10007791-1705591800-1705595400@seasevents.nmsdev7.com
SUMMARY:BE Seminar: "Toward a multi-task\, multi-source foundation model to advance large-scale neural data analysis" (Eva Dyer\, Georgia Tech)
DESCRIPTION:Neuroscience datasets are expanding rapidly in both size and volume. However\, integrating information across diverse datasets to form a unified understanding of brain function remains challenging. In this talk\, I will discuss our initiatives to combine datasets from various tasks\, brain regions\, and species into a unified ‘neurofoundation’ model. This foundational model promises to enhance data efficiency\, brain-machine interface and neural decoder capabilities\, and offer advanced\, user-friendly tools to the broader neuroscience community. These efforts mark a significant step towards a more integrated methodology in neural data analysis.
URL:https://seasevents.nmsdev7.com/event/be-seminar-eva-dyer-georgia-tech/
LOCATION:Raisler Lounge (Room 225)\, Towne Building\, 220 South 33rd Street\, Philadelphia\, PA\, 19104\, United States
CATEGORIES:Seminar
ORGANIZER;CN="Bioengineering":MAILTO:be@seas.upenn.edu
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20240122T130000
DTEND;TZID=America/New_York:20240122T150000
DTSTAMP:20260404T085842
CREATED:20240110T173949Z
LAST-MODIFIED:20240110T173949Z
UID:10007800-1705928400-1705935600@seasevents.nmsdev7.com
SUMMARY:BE Doctoral Dissertation Defense: "Harnessing Regnase-1 and Roquin-1 activity to modulate T cell function" (David Mai)
DESCRIPTION:The Department of Bioengineering at the University of Pennsylvania and Dr. Carl June are pleased to announce the Doctoral Dissertation Defense of David Mai.\n \n\nDate: January 22\, 2024\nTime: 1PM EST\n\n\nTitle: Harnessing Regnase-1 and Roquin-1 activity to modulate T cell function\nLocation: Arthur H Rubenstein Auditorium (https://www.itmat.upenn.edu/itmat/education-and-training/assets/user-content//documents/DirectionsSmilowCTRAuditorium.pdf)\n\n\nZoom link\n\n\nThe public is welcome to attend.
URL:https://seasevents.nmsdev7.com/event/be-doctoral-dissertation-defense-harnessing-regnase-1-and-roquin-1-activity-to-modulate-t-cell-function-david-mai/
LOCATION:Arthur H Rubenstein Auditorium\, 3400 Civic Center Boulevard\, Philadelphia\, PA\, 19104\, United States
CATEGORIES:Doctoral,Graduate,Student,Dissertation or Thesis Defense
ORGANIZER;CN="Bioengineering":MAILTO:be@seas.upenn.edu
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20240123T100000
DTEND;TZID=America/New_York:20240123T113000
DTSTAMP:20260404T085842
CREATED:20240116T150642Z
LAST-MODIFIED:20240116T150642Z
UID:10007802-1706004000-1706009400@seasevents.nmsdev7.com
SUMMARY:MEAM Seminar: "Transport and Delivery by Active Materials"
DESCRIPTION:One of the major challenges in robotics is controlling micromanipulation by active and adaptive materials. Existing delivery technologies often suffer from limited navigation control\, low speeds\, and proneness to environmental disturbances. Biology often solves these problems by collectively organizing actuation at the microscale. For example\, pathogens are removed from our lungs by an active carpet of cilia [1]. Inside these cilia\, in turn\, microtubules form highways for molecular motors. In this talk\, I will present developments in the microfabrication of “artificial cilia” [2] and “artificial microtubules” [3]. We designed amphibious cilia that can transport both liquids and dry objects. These carpets can sort particles by size and by shape using a crowd-surfing effect. We also designed magnetic microtubules\, structured microfibers that rapidly guide particles through flow networks such as the cardiovascular system. These works offer unique strategies for robust microscale delivery\, but equally shed light on non-equilibrium diffusion [4] in biological transport processes. \n[1] Ramirez-San Juan GR et al. “Multi-scale spatial heterogeneity enhances particle clearance in airway ciliary arrays”\, Nat. Phys. 16: 958–964 (2020) \n[2] Demirörs AF et al. “Amphibious transport of fluids and solids by soft magnetic carpets”\, Adv. Sci. 202102510 (2021) \n[3] Gu H et al. “Artificial microtubules for rapid and collective transport of magnetic microcargos”\, Nat. Mach. Intel. 4: 678–684 (2022) \n[4] Guzman-Lastra F et al. “Active carpets drive non-equilibrium diffusion and enhanced molecular fluxes\,” Nat. Commun. 12: 1906 (2021)
URL:https://seasevents.nmsdev7.com/event/meam-seminar-transport-and-delivery-by-active-materials/
LOCATION:Wu and Chen Auditorium (Room 101)\, Levine Hall\, 3330 Walnut Street\, Philadelphia\, PA\, 19104\, United States
CATEGORIES:Seminar
ORGANIZER;CN="Mechanical Engineering and Applied Mechanics":MAILTO:meam@seas.upenn.edu
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20240124T120000
DTEND;TZID=America/New_York:20240124T131500
DTSTAMP:20260404T085842
CREATED:20230928T142208Z
LAST-MODIFIED:20230928T142208Z
UID:10007712-1706097600-1706102100@seasevents.nmsdev7.com
SUMMARY:ASSET Seminar: "Learning to Read X-Ray: Applications to Heart Failure Monitoring" (Polina Golland\, Massachusetts Institute of Technology)
DESCRIPTION:ABSTRACT: \nWe propose and demonstrate a novel approach to training image classification models based on large collections of images with limited labels. We take advantage of availability of radiology reports to construct joint multimodal embedding that serves as a basis for classification. We demonstrate the advantages of this approach in application to assessment of pulmonary edema severity in congestive heart failure that motivated the development of the method.
URL:https://seasevents.nmsdev7.com/event/asset-seminar-polina-golland-massachusetts-institute-of-technology/
LOCATION:Raisler Lounge (Room 225)\, Towne Building\, 220 South 33rd Street\, Philadelphia\, PA\, 19104\, United States
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20240124T153000
DTEND;TZID=America/New_York:20240124T163000
DTSTAMP:20260404T085842
CREATED:20240116T174749Z
LAST-MODIFIED:20240116T174749Z
UID:10007804-1706110200-1706113800@seasevents.nmsdev7.com
SUMMARY:CBE Seminar: "Bioinspired Protein-Based Cancer Immunotherapy" (Yanpu He\, MIT)
DESCRIPTION:Abstract:\nImmunotherapy has revolutionized the field of cancer treatment over the past two decades\, though only a small fraction of patients treated will achieve complete remission. As such\, new paradigms to overcome resistance to immunotherapies are urgently needed. My research seeks to tailor immunotherapies towards individual differences in immune systems and the inherent heterogeneity of cancer. For this talk\, I will share my work on a key therapeutic target against cancer called the STimulator of INterferon Genes (STING) signaling. I first addressed an innate immunodeficiency caused by a loss-of-function mutation of STING protein affecting 20% of the human population\, using the cytosolic domain of STING (STINGΔTM) as a functional agonist carrier to activate signaling in STING-deficient cells. Subsequently\, I developed a therapeutic cancer vaccine based on this platform by fusing STINGΔTM with immune checkpoint blockade (ICB) nanobodies. The treatment eliminated subcutaneous colon and melanoma tumors in 70-100% of mice and protected all cured mice against rechallenge\, while mechanistic studies revealed a distinct STING-mediated anti-tumor immunity driven by robust TH1 polarization and Treg suppression in CD4+ T cells\, followed by the collaboration of CD8+ T and NK cells to eliminate tumors. For my independent group\, I will continue these prospects in designing protein therapeutics and leveraging the full potential of CD4+ T cells\, initially towards personalized cancer immunotherapies and expanding to other monogenic immunodeficiencies and drug delivery challenges in the long run.
URL:https://seasevents.nmsdev7.com/event/cbe-seminar-bioinspired-protein-based-cancer-immunotherapy-yanpu-he-mit/
LOCATION:Wu and Chen Auditorium (Room 101)\, Levine Hall\, 3330 Walnut Street\, Philadelphia\, PA\, 19104\, United States
CATEGORIES:Seminar
ORGANIZER;CN="Chemical and Biomolecular Engineering":MAILTO:cbemail@seas.upenn.edu
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20240125T150000
DTEND;TZID=America/New_York:20240125T160000
DTSTAMP:20260404T085842
CREATED:20240109T145748Z
LAST-MODIFIED:20240109T145748Z
UID:10007798-1706194800-1706198400@seasevents.nmsdev7.com
SUMMARY:ESE Grace Hopper Lecture - "Disrupting NextG"
DESCRIPTION:As 5G takes to the airwaves\, we now turn our imagination to the next generation of wireless technology. The promise of this technology has created an international race to innovate\, with significant investment by government as well as industry. And much innovation is needed as 6G aspires to not only support significantly higher data rates than 5G\, but also improved reliability along with excellent coverage indoors and out\, including for underserved areas. New architectures including edge computing must be designed to drastically enhance efficient resource allocation while also reducing latency for real-time control. Breakthrough energy-efficiency architectures\, algorithms and hardware will be needed so that wireless devices can be powered by tiny batteries\, energy-harvesting\, or over-the-air power transfer. And machine learning may will play a big role in the underlying technologies for NextG as well as the “killer apps” that will drive its deployment and success. This talk will describe what the wireless future might look like along with some of the innovations and breakthroughs required to realize this vision.
URL:https://seasevents.nmsdev7.com/event/ese-grace-hopper-lecture-title-tbd/
LOCATION:Glandt Forum\, Singh Center for Nanotechnology\, 3205 Walnut Street\, Philadelphia\, PA\, 19104\, United States
CATEGORIES:Distinguished Lecture
ORGANIZER;CN="Electrical and Systems Engineering":MAILTO:eseevents@seas.upenn.edu
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20240126T103000
DTEND;TZID=America/New_York:20240126T114500
DTSTAMP:20260404T085842
CREATED:20230824T135007Z
LAST-MODIFIED:20230824T135007Z
UID:10007643-1706265000-1706269500@seasevents.nmsdev7.com
SUMMARY:Spring 2024 GRASP on Robotics: Dinesh Manocha\, University of Maryland\, College Park\, “Robot Navigation in Complex Indoor and Outdoor Environments”
DESCRIPTION:This is a hybrid event with in-person attendance in Wu and Chen and virtual attendance on Zoom. \nABSTRACT\nIn the last few decades\, most robotics success stories have been limited to structured or controlled environments. A major challenge is to develop robot systems that can operate in complex or unstructured environments corresponding to homes\, dense traffic\, outdoor terrains\, public places\, etc. In this talk\, we give an overview of our ongoing work on developing robust planning and navigation technologies that use recent advances in computer vision\, sensor technologies\, machine learning\, and motion planning algorithms. We present new methods that utilize multi-modal observations from an RGB camera\, 3D LiDAR\, and robot odometry for scene perception\, along with deep reinforcement learning for reliable planning. The latter is also used to compute dynamically feasible and spatial aware velocities for a robot navigating among mobile obstacles and uneven terrains. We have integrated these methods with wheeled robot and legged platforms and highlight their performance in crowded indoor scenes and dense outdoor terrains.
URL:https://seasevents.nmsdev7.com/event/spring-2024-grasp-on-robotics-dinesh-manocha-university-of-maryland-robot-navigation-in-complex-indoor-and-outdoor-environments/
LOCATION:Wu and Chen Auditorium (Room 101)\, Levine Hall\, 3330 Walnut Street\, Philadelphia\, PA\, 19104\, United States
CATEGORIES:Seminar
ORGANIZER;CN="General Robotics%2C Automation%2C Sensing and Perception (GRASP) Lab":MAILTO:grasplab@seas.upenn.edu
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20240126T141500
DTEND;TZID=America/New_York:20240126T150000
DTSTAMP:20260404T085842
CREATED:20240122T191258Z
LAST-MODIFIED:20240122T191258Z
UID:10007819-1706278500-1706281200@seasevents.nmsdev7.com
SUMMARY:PICS Colloquium: "An introduction to neural ODEs in scientific machine learning."
DESCRIPTION:This is a quick introduction to neural ODEs for scientific applications. The goal is to (a) provide a modelling tool that enhances the expressivity of existing theory-driven approaches\, (b) demonstrate that neural ODEs are easy to use via modern autodifferentiable software\, and (c) give enough of the tips-and-tricks needed to make neural ODEs work in practice! \nZoom link: https://upenn.zoom.us/j/96060692429
URL:https://seasevents.nmsdev7.com/event/pics-colloquium-an-introduction-to-neural-odes-in-scientific-machine-learning/
LOCATION:Zoom
CATEGORIES:Colloquium
ORGANIZER;CN="Penn Institute for Computational Science (PICS)":MAILTO:dkparks@seas.upenn.edu
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20240130T100000
DTEND;TZID=America/New_York:20240130T113000
DTSTAMP:20260404T085842
CREATED:20240117T161205Z
LAST-MODIFIED:20240117T161205Z
UID:10007817-1706608800-1706614200@seasevents.nmsdev7.com
SUMMARY:MEAM Seminar: "Making Dynamic Robots Taskable"
DESCRIPTION:In this talk\, I will share some insights and observations from our work on Atlas\, the world’s most dynamic humanoid robot. I’ll talk about some of the core ideas—like model-predictive control (MPC)—that have made an impact for us\, how learning is playing a larger role in how we design control systems at Boston Dynamics\, and how we think about scaling up through real world deployments.
URL:https://seasevents.nmsdev7.com/event/meam-seminar-making-dynamic-robots-taskable/
LOCATION:Wu and Chen Auditorium (Room 101)\, Levine Hall\, 3330 Walnut Street\, Philadelphia\, PA\, 19104\, United States
ORGANIZER;CN="Mechanical Engineering and Applied Mechanics":MAILTO:meam@seas.upenn.edu
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20240130T153000
DTEND;TZID=America/New_York:20240130T163000
DTSTAMP:20260404T085842
CREATED:20240124T153237Z
LAST-MODIFIED:20240124T153237Z
UID:10007823-1706628600-1706632200@seasevents.nmsdev7.com
SUMMARY:CIS Seminar: "Obfuscation of Quantum Computation"
DESCRIPTION:Protecting secrets within computer systems is a central mission of cryptography. Program obfuscation\, which scrambles computer code without harming its functionality\, is an immensely powerful and versatile tool for accomplishing this task that has been the subject of intense study in classical cryptography. Yet\, the ability to obfuscate quantum computation had previously remained elusive to researchers\, even with the widespread use of quantum technology on the horizon. \nThis talk will demonstrate how quantum information-processing systems can keep secrets\, and explore the implications of this ability. In particular\, we will cover a series of recent results that establish the feasibility of obfuscating general-purpose quantum computation\, and reveal deep connections with several important fields of study within quantum computational science\, including verification of quantum computation and unclonable cryptography.
URL:https://seasevents.nmsdev7.com/event/cis-seminar-obfuscation-of-quantum-computation/
LOCATION:Wu and Chen Auditorium (Room 101)\, Levine Hall\, 3330 Walnut Street\, Philadelphia\, PA\, 19104\, United States
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20240131T120000
DTEND;TZID=America/New_York:20240131T133000
DTSTAMP:20260404T085842
CREATED:20240125T160426Z
LAST-MODIFIED:20240125T160426Z
UID:10007826-1706702400-1706707800@seasevents.nmsdev7.com
SUMMARY:ASSET Seminar: “Towards A New Frontier of Trustworthy AI: Interpretable Machine Learning Algorithms that Produce All Good Models” (Chudi Zhong\, Duke University)
DESCRIPTION:ABSTRACT: \nMachine learning has been increasingly deployed for high-stakes decisions that deeply impact people’s lives. My research focuses on developing interpretable algorithms and pipelines to ensure the safe and efficient utilization of machine learning models in the decision-making process. In this talk\, I will introduce a new paradigm\, called learning the Rashomon set\, which finds and stores all models within epsilon of the optimal loss. I will present algorithms for finding optimal models and Rashomon sets\, discuss how this new paradigm can break the interaction bottleneck between users and ML algorithms\, and provide examples of its applications. \n  \nZOOM LINK (if unable to attend in-person): https://upenn.zoom.us/j/99641494762 \n 
URL:https://seasevents.nmsdev7.com/event/asset-seminar-towards-a-new-frontier-of-trustworthy-ai-interpretable-machine-learning-algorithms-that-produce-all-good-models-chudi-zhong-duke-university/
LOCATION:Raisler Lounge (Room 225)\, Towne Building\, 220 South 33rd Street\, Philadelphia\, PA\, 19104\, United States
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20240131T150000
DTEND;TZID=America/New_York:20240131T160000
DTSTAMP:20260404T085842
CREATED:20240122T192113Z
LAST-MODIFIED:20240122T192113Z
UID:10007820-1706713200-1706716800@seasevents.nmsdev7.com
SUMMARY:Spring 2024 GRASP SFI: Raphael Zufferey\, École Polytechnique Fédérale de Lausanne\, "Flying robots: exploring hybrid locomotion and physical interaction"
DESCRIPTION:This will be a hybrid event with in-person attendance in Levine 307 and virtual attendance on Zoom. This week’s speaker will be virtual. \nABSTRACT\nAutonomous flying robots have become widespread in recent years\, yet their capability to interact with the environment. remains limited. Moving in multiple fluids is one of the great challenges of mobile robotics\, and carries great potential for application in biological and environmental studies. In particular\, hybrid locomotion provides the means to cross large distances and obstacles or even change from one body of water to another thanks to flight. At the same time\, they are capable of operating underwater\, collecting samples\, video and aquatic metrics. However\, the challenges of operating in both air and water are complex. In this talk\, we will introduce these challenges and cover several research solutions which aim to adress these in different modalities\, depending on locomotion and objectives. Bio-inspiration plays a crucial role in these solutions\, and the topic of flapping flight in the context of physical interaction will also be presented.
URL:https://seasevents.nmsdev7.com/event/spring-2024-grasp-sfi-raphael-zufferey/
LOCATION:Levine 307\, 3330 Walnut Street\, Philadelphia\, PA\, 19104\, United States
CATEGORIES:Seminar
ORGANIZER;CN="General Robotics%2C Automation%2C Sensing and Perception (GRASP) Lab":MAILTO:grasplab@seas.upenn.edu
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20240131T153000
DTEND;TZID=America/New_York:20240131T163000
DTSTAMP:20260404T085842
CREATED:20240116T175241Z
LAST-MODIFIED:20240116T175241Z
UID:10007805-1706715000-1706718600@seasevents.nmsdev7.com
SUMMARY:CBE Seminar: "Optimal Control as a catalyst for Smart and Sustainable Systems" (Benjamin Decardi-Nelson\, Cornell)
DESCRIPTION:Abstract:\nIn modern engineering\, sustainability is a crucial aspect\, especially in chemical and biological process systems. This concept has evolved to encompass a holistic approach\, emphasizing not only the use of sustainable resources but also the development of systems that are environmentally friendly\, smart\, and efficient. Such systems aim to minimize waste and optimize resource use. At the heart of this shift is optimal control\, a fundamental element in engineering smart\, sustainable systems. However\, the integration of optimal control technologies into these systems is challenging due to the complexity of managing large-scale\, constrained\, nonlinear\, and interconnected subsystems\, particularly under uncertain conditions. In this talk\, I will introduce a series of optimal control technologies that contribute to smarter and more efficient systems\, enhancing their sustainability. Specifically\, I will discuss the development and application of (1) model predictive control and (2) reinforcement learning\, which are instrumental in creating systems that use minimal resources and generate less waste. I will also demonstrate how optimal control is pivotal in advancing sustainable food production in urban areas through the integration of renewable energy and efficient resource management. Overall\, these advancements in optimal control techniques illustrate their transformative role in shaping the future of intelligent\, sustainable systems\, underscoring their vital importance in our path toward a more sustainable world.
URL:https://seasevents.nmsdev7.com/event/cbe-seminar-optimal-control-as-a-catalyst-for-smart-and-sustainable-systems-benjamin-decardi-nelson-cornell/
LOCATION:Wu and Chen Auditorium (Room 101)\, Levine Hall\, 3330 Walnut Street\, Philadelphia\, PA\, 19104\, United States
CATEGORIES:Seminar
ORGANIZER;CN="Chemical and Biomolecular Engineering":MAILTO:cbemail@seas.upenn.edu
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20240201T153000
DTEND;TZID=America/New_York:20240201T163000
DTSTAMP:20260404T085842
CREATED:20240108T171010Z
LAST-MODIFIED:20240108T171010Z
UID:10007792-1706801400-1706805000@seasevents.nmsdev7.com
SUMMARY:BE Seminar: "Imaging the Brain for Deeper\, Finer\, and More Diverse Insight" (Fei Xia\, Ecole Normale Supérieure)
DESCRIPTION:The brain is a powerful organ that regulates health and drives intelligence. How can we see more clearly into the working brain to understand it better? High-resolution optical microscopy has long been an ideal tool due to its spatial sub-micron precision and specificity. However\, achieving the necessary spatio-temporal scale for further advancing our understanding of the brain remains a challenge. The primary obstacle originates from the inhomogeneous nature of tissues\, which distort light and compromise imaging depth\, precision\, and information. \nIn this talk\, I will introduce new in vivo deep tissue optical microscopy platforms advanced in microscope design and computational tools\, to address existing challenges. By moving towards longer wavelengths for one-\, two-\, and three-photon microscopy\, we have achieved simultaneous deep structural and functional imaging through an entire cortical column with multiple label-free and fluorescence contrasts. With precise control of light\, we have enabled adaptive optical imaging of dendritic spines and myelinated axons up to the hippocampus. With a new AI-enabled tool\, we have sped up volumetric 3D imaging for microvasculature\, neurons\, and dendrites. These techniques advance toward imaging the dynamic\, cell-type-specific processes and microvasculature within the living brain. I will conclude by discussing the opportunities these enabling optical microscopy techniques offer for biology and clinical applications.
URL:https://seasevents.nmsdev7.com/event/be-seminar-fei-xia-ecole-normale-superieure/
LOCATION:Raisler Lounge (Room 225)\, Towne Building\, 220 South 33rd Street\, Philadelphia\, PA\, 19104\, United States
CATEGORIES:Seminar
ORGANIZER;CN="Bioengineering":MAILTO:be@seas.upenn.edu
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20240202T103000
DTEND;TZID=America/New_York:20240202T114500
DTSTAMP:20260404T085842
CREATED:20240126T155547Z
LAST-MODIFIED:20240126T155547Z
UID:10007831-1706869800-1706874300@seasevents.nmsdev7.com
SUMMARY:Spring 2024 GRASP on Robotics: John Doyle\, California Institute of Technology\, "Control/Architecture/Control"
DESCRIPTION:This is a hybrid event with a VIRTUAL SPEAKER. There will be in-person attendance in Wu and Chen and virtual attendance on Zoom. \nABSTRACT\nThis talk will describe progress in developing a universal theory of architectures for complex networks\, motivated by and applied to aerospace\, process control\, internet\, cyberphysical\, ecosystems\, multiscale physics\, turbulence\, biology\, neuroscience\, medicine\, linguistics\, and social systems.
URL:https://seasevents.nmsdev7.com/event/spring-2024-grasp-on-robotics-john-doyle-california-institute-of-technology-control-architecture-control/
LOCATION:Wu and Chen Auditorium (Room 101)\, Levine Hall\, 3330 Walnut Street\, Philadelphia\, PA\, 19104\, United States
CATEGORIES:Seminar
ORGANIZER;CN="General Robotics%2C Automation%2C Sensing and Perception (GRASP) Lab":MAILTO:grasplab@seas.upenn.edu
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20240202T140000
DTEND;TZID=America/New_York:20240202T150000
DTSTAMP:20260404T085842
CREATED:20240123T174255Z
LAST-MODIFIED:20240123T174255Z
UID:10007821-1706882400-1706886000@seasevents.nmsdev7.com
SUMMARY:PICS Colloquium: "Exploring the landscape of model representations"
DESCRIPTION:Many studies adopt low-resolution\, coarse-grained (CG) models to investigate polymers\, proteins\, and other soft materials. These studies must first specify the details that are retained in the low-resolution model\, i.e.\, they must specify the “CG representation.” Unfortunately\, the “best” representation for complex systems is not always obvious. In this study\, we systematically explore the space of model representations for a typical protein and we examine how the properties of the CG model depend upon the choice of representation\, i.e.\, the details retained in the CG model. By adopting a simple high-resolution model for protein fluctuations\, we quantitatively assess the quality of a representation based upon its information content\, I\, and spectral quality\, Q. While I quantifies the information lost due to eliminating details from the high-resolution model\, Q quantifies the extent to which the representation preserves large scale motions. By employing these metrics as energy functions and adopting an ergodic move set\, we explore the local and global minima in the space of representations. Additionally\, by employing Monte Carlo methods\, we quantify the number of representations with a given quality. We find that representations with high spectral quality match our physical intuition\, while highly informative representations do not. Indeed\, we find that the information content and spectral quality are anti-correlated among low-resolution representations. Moreover\, our study suggests the possibility of a critical resolution below which there may exist a “phase transition” distinguishing good and bad representations. These studies may provide insight for developing CG models of soft materials and\, more generally\, for developing reduced representations of complex phenomena or high-dimensional data.
URL:https://seasevents.nmsdev7.com/event/pics-colloquium-exploring-the-landscape-of-model-representations/
LOCATION:PICS Conference Room 534 – A Wing \, 5th Floor\, 3401 Walnut Street\, Philadelphia\, PA\, 19104\, United States
CATEGORIES:Colloquium
ORGANIZER;CN="Penn Institute for Computational Science (PICS)":MAILTO:dkparks@seas.upenn.edu
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20240205T153000
DTEND;TZID=America/New_York:20240205T163000
DTSTAMP:20260404T085842
CREATED:20231219T204537Z
LAST-MODIFIED:20231219T204537Z
UID:10007786-1707147000-1707150600@seasevents.nmsdev7.com
SUMMARY:Penn Engineering 2023-24 Pender Award Lecture: Shafi Goldwasser
DESCRIPTION:
URL:https://seasevents.nmsdev7.com/event/penn-engineering-2023-24-pender-award-lecture-shafi-goldwasser/
LOCATION:Wu and Chen Auditorium (Room 101)\, Levine Hall\, 3330 Walnut Street\, Philadelphia\, PA\, 19104\, United States
CATEGORIES:Seminar,Distinguished Lecture,Faculty
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20240206T100000
DTEND;TZID=America/New_York:20240206T113000
DTSTAMP:20260404T085842
CREATED:20240116T230557Z
LAST-MODIFIED:20240116T230557Z
UID:10007816-1707213600-1707219000@seasevents.nmsdev7.com
SUMMARY:MEAM Seminar: “Towards the Discovery of Trustworthy and Interpretable ML-enabled Constitutive Laws for Solids from Low- and Limited-data”
DESCRIPTION:Machine learning techniques are gearing up to play a significant role in the field of computational solid mechanics and multiphysics\, enabling the integration of experimental data and physical constraints towards data-driven constitutive laws\, acceleration of computational techniques for multi-scale modeling\, and new paradigms for the solution of forward and inverse problems\, to name a few. This talk will cover recent advancements in the area of ML-enabled constitutive modeling I) A physics-informed data-driven constitutive modeling approach for isotropic and anisotropic hyperelastic materials is developed using tensor representation theorems. The trained surrogates (using GPR and NNs) are able to respect physical principles such as material frame indifference\, material symmetry\, and the local balance of angular momentum. Overall\, the presented approach is tested on synthetic data from isotropic and anisotropic constitutive laws and shows surprising accuracy even far beyond the limits of the training domain\, indicating that the resulting surrogates can efficiently generalize as they incorporate knowledge about the underlying physics. Additionally it is shown that the inherent material symmetries can be discovered directly from data. II) Finally\, we proceed to tackle elastoplasticity in a modular framework. Employing convexity for the yield functions we recover textrure-parametrized yield functions using input convex (IC)NNs and propose a hybrid model-data-driven framework to recover yield functions with tension compression asymmetries in the low data regime. Additionally by employing thermodynamic requirements in an NN-based framework we learn hardening laws from limited experimental data. III) The extension of the above approaches for both hyperelasticity and elastoplasticity to enable interpretable discovery of constitutive models without the use of model libraries will be discussed. IV) Finally ML-hybrid approaches for the solution of PDEs will be introduced\, focusing on applications in solid and structural mechanics towards high dimensional optimization problems requiring robust and trustworthy solvers.
URL:https://seasevents.nmsdev7.com/event/meam-seminar-towards-the-discovery-of-trustworthy-and-interpretable-ml-enabled-constitutive-laws-for-solids-from-low-and-limited-data/
LOCATION:Wu and Chen Auditorium (Room 101)\, Levine Hall\, 3330 Walnut Street\, Philadelphia\, PA\, 19104\, United States
ORGANIZER;CN="Mechanical Engineering and Applied Mechanics":MAILTO:meam@seas.upenn.edu
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20240206T153000
DTEND;TZID=America/New_York:20240206T163000
DTSTAMP:20260404T085842
CREATED:20240124T182229Z
LAST-MODIFIED:20240124T182229Z
UID:10007824-1707233400-1707237000@seasevents.nmsdev7.com
SUMMARY:CIS Seminar: " How Algorithms Can Support Deliberative Democracy"
DESCRIPTION:Academics and political practitioners around the world are experimenting with a class of democratic innovations called deliberative mini-publics (DMs). In a DM\, a panel of constituents convenes to deliberate about specific issues and make policy recommendations to traditional political decision-makers (e.g.\, legislators). Nearly all DMs rely on sortition – random selection – to choose the panelists. Sortition is often thought of as a simple lottery that chooses all constituents with equal probability. In practice\, however\, simple random selection fails to yield representative panels due to selection bias in who accepts invitations to participate. Many practitioners of DMs therefore sacrifice the pure equality embodied by a simple lottery\, instead imposing quotas on socially salient groups and then “randomizing” within those constraints. \nEngineering this randomization within user-specified quotas turns out to be technically demanding. My talk covers our algorithmic solution to this problem: a framework of optimization-based algorithms which\, subject to such quotas\, ensure individuals’ selection probabilities are as equal as possible\, as measured by any convex function measuring equality (Fair Algorithms for Selecting Citizens’ Assemblies\, Nature\, ‘21). \nAfter presenting our approach to this technical problem\, I discuss my follow-up work demonstrating how the notion of equality we choose to optimize within this framework has implications for normative goals like fairness\, transparency\, and resistance to subversion. This includes a discussion of Leximin\, the original instantiation of our framework\, which has been adopted widely in practice and is available for public use at Panelot.org.
URL:https://seasevents.nmsdev7.com/event/cis-seminar-how-algorithms-can-support-deliberative-democracy/
LOCATION:Wu and Chen Auditorium (Room 101)\, Levine Hall\, 3330 Walnut Street\, Philadelphia\, PA\, 19104\, United States
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20240207T103000
DTEND;TZID=America/New_York:20240207T113000
DTSTAMP:20260404T085842
CREATED:20240202T144841Z
LAST-MODIFIED:20240202T144841Z
UID:10007846-1707301800-1707305400@seasevents.nmsdev7.com
SUMMARY:Spring 2024 GRASP SFI: Andrew Owens\, University of Michigan\, "Multimodal Learning from the Bottom Up"
DESCRIPTION:This will be a hybrid event with in-person attendance in Levine 307 and virtual attendance on Zoom. \nABSTRACT\nToday’s machine perception systems rely extensively on supervision provided by humans\, such as natural language. I will talk about our efforts to make systems that\, instead\, learn from two ubiquitous sources of unlabeled sensory data: visual motion and cross-modal associations between senses. First\, I will discuss our work on creating unified self-supervised motion analysis methods that can address both object tracking and optical flow tasks. I will then discuss how these same techniques can be applied to localizing sound sources in video\, and how tactile sensing data can be used to train multimodal  visual-tactile models. Finally\, I will talk about our recent work on subverting visual perception systems\, by creating “multi-view” optical illusions: images that change their appearance under a transformation\, such as a flip or rotation.
URL:https://seasevents.nmsdev7.com/event/spring-2024-grasp-sfi-andrew-owens/
LOCATION:Levine 307\, 3330 Walnut Street\, Philadelphia\, PA\, 19104\, United States
CATEGORIES:Seminar
ORGANIZER;CN="General Robotics%2C Automation%2C Sensing and Perception (GRASP) Lab":MAILTO:grasplab@seas.upenn.edu
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20240207T120000
DTEND;TZID=America/New_York:20240207T133000
DTSTAMP:20260404T085842
CREATED:20240125T211658Z
LAST-MODIFIED:20240125T211658Z
UID:10007828-1707307200-1707312600@seasevents.nmsdev7.com
SUMMARY:ASSET Seminar: "Paths to AI Accountability" (Sarah Cen\, Massachusetts Institute of Technology)
DESCRIPTION:ABSTRACT: \nIn the past decade\, we have begun grappling with difficult questions related to the rise of AI\, including: What rights do individuals have in the age of AI? When should we regulate AI and when should we abstain? What degree of transparency is needed to monitor AI systems? These questions are all concerned with AI accountability: determining who owes responsibility and to whom in the age of AI. In this talk\, I will discuss the two main components of AI accountability\, then illustrate them through a case study on social media. Within the context of social media\, I will focus on how social media platforms filter (or curate) the content that users see. I will review several methods for auditing social media\, drawing from concepts and tools in hypothesis testing\, causal inference\, and LLMs. \n  \nZOOM LINK (if unable to attend in-person): https://upenn.zoom.us/j/96315573573 \n 
URL:https://seasevents.nmsdev7.com/event/asset-seminar-sarah-cen-massachusetts-institute-of-technology/
LOCATION:Raisler Lounge (Room 225)\, Towne Building\, 220 South 33rd Street\, Philadelphia\, PA\, 19104\, United States
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20240207T153000
DTEND;TZID=America/New_York:20240207T163000
DTSTAMP:20260404T085842
CREATED:20240116T175613Z
LAST-MODIFIED:20240116T175613Z
UID:10007806-1707319800-1707323400@seasevents.nmsdev7.com
SUMMARY:CBE Seminar: "Molecular Microscopy with Single Cell Transcriptomic Data Resolves RNA Liquid Biopsies" (Sevahn Vorperian\, Stanford)
DESCRIPTION:Abstract\nInvasive biopsy is the gold standard for diagnosing several diseases; however\, these procedures offer a limited\, localized view of the disease pathology to the physician and are not risk-free to the patient. Cell-free RNA (cfRNA) in blood plasma reflects dynamic gene expression changes and can facilitate early disease diagnosis\, yet current cfRNA assays fall short of the cellular resolution afforded by an invasive biopsy. In this talk\, I will first resolve plasma cfRNA at cell type resolution using single cell transcriptomic data alongside approaches from machine learning and data science\, which enable a systems-view into the underlying molecular patterns within these high-dimensional biological data. I will then describe how this molecular microscope can noninvasively reflect changes observed in invasive biopsy across various diseases and facilitate the study of biofluids beyond the blood. These findings expand the achievable resolution within the RNA liquid biopsy biomolecular repertoire and broaden opportunities in precision medicine for complex diseases in hard-to-biopsy tissues.
URL:https://seasevents.nmsdev7.com/event/cbe-seminar-molecular-microscopy-with-single-cell-transcriptomic-data-resolves-rna-liquid-biopsies-sevahn-vorperian-stanford/
LOCATION:Wu and Chen Auditorium (Room 101)\, Levine Hall\, 3330 Walnut Street\, Philadelphia\, PA\, 19104\, United States
CATEGORIES:Seminar
ORGANIZER;CN="Chemical and Biomolecular Engineering":MAILTO:cbemail@seas.upenn.edu
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20240208T150000
DTEND;TZID=America/New_York:20240208T170000
DTSTAMP:20260404T085842
CREATED:20240201T155129Z
LAST-MODIFIED:20240201T155129Z
UID:10007845-1707404400-1707411600@seasevents.nmsdev7.com
SUMMARY:Evolution of Data Storytelling: Women in Data Science x Penn Museum Tour + Workshop
DESCRIPTION:Join us for an exciting kick-off event at the Penn Museum as part of the Women in Data Science (WiDS) @ Penn conference\, where the past meets the future in a guided tour and storytelling workshop.
URL:https://seasevents.nmsdev7.com/event/evolution-of-data-storytelling-women-in-data-science-x-penn-museum-tour-workshop/
LOCATION:The Penn Museum\, 3260 South St\, Philadelphia\, PA\, 19104\, United States
CATEGORIES:Workshop
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20240208T153000
DTEND;TZID=America/New_York:20240208T163000
DTSTAMP:20260404T085842
CREATED:20240116T154201Z
LAST-MODIFIED:20240116T154201Z
UID:10007803-1707406200-1707409800@seasevents.nmsdev7.com
SUMMARY:BE Seminar: "Mapping and engineering gene expression with chemical and spatial lenses" (Hailing Shi\, Broad Institute & MIT)
DESCRIPTION:Precise RNA expression\, tailored to specific brain regions\, cell types\, and subcellular compartments\, is pivotal for orchestrating complex brain functions. In the first part of my talk\, I will introduce a confocal imaging-based spatial transcriptomics platform\, STARmap\, that seamlessly combines in situ hybridization\, hydrogel tissue chemistry\, and in situ sequencing technologies. Leveraging scalable experimental and computational pipelines\, we have constructed a comprehensive spatial cell atlas of the mouse brain\, revealing subregion-specific cell types\, previously undiscovered tissue architectures\, and viral tropisms. The second part of my talk transits to chemical modifications on messenger RNAs (mRNAs) and their far-reaching implications in gene expression regulation and the development of RNA therapeutics. I will discuss the messenger-oligonucleotide conjugate RNAs (mocRNAs) design\, showcasing how we can harness chemical modifications for engineering enhanced gene delivery vectors. Looking into the future\, I aim to innovate and integrate chemical and spatial profiling approaches to understand tissue health and disease in-depth.
URL:https://seasevents.nmsdev7.com/event/be-seminar-mapping-and-engineering-gene-expression-with-chemical-and-spatial-lenses-hailing-shi-broad-institute-mit/
LOCATION:Raisler Lounge (Room 225)\, Towne Building\, 220 South 33rd Street\, Philadelphia\, PA\, 19104\, United States
CATEGORIES:Seminar
ORGANIZER;CN="Bioengineering":MAILTO:be@seas.upenn.edu
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20240208T153000
DTEND;TZID=America/New_York:20240208T163000
DTSTAMP:20260404T085842
CREATED:20240129T163131Z
LAST-MODIFIED:20240129T163131Z
UID:10007832-1707406200-1707409800@seasevents.nmsdev7.com
SUMMARY:CIS Seminar: "Rethinking Data Use in Large Language Models"
DESCRIPTION:Large language models (LMs) such as ChatGPT have revolutionized natural language processing and artificial intelligence more broadly. In this talk\, I will discuss my research on understanding and advancing these models\, centered around how they use the very large text corpora they are trained on. First\, I will describe our efforts to understand how these models learn to perform new tasks after training\, demonstrating that their so-called in context learning capabilities are almost entirely determined by what they learn from the training data. Next\, I will introduce a new class of LMs—nonparametric LMs—that repurpose this training data as a data store from which they retrieve information for improved accuracy and updatability. I will describe my work on establishing the foundations of such models\, including one of the first broadly used neural retrieval models and an approach that simplifies a traditional\, two-stage pipeline into one. I will also discuss how nonparametric models open up new avenues for responsible data use\, e.g.\, by segregating permissive and copyrighted text and using them differently. Finally\, I will envision the next generation of LMs we should build\, focusing on efficient scaling\, improving factuality\, and decentralization.
URL:https://seasevents.nmsdev7.com/event/cis-seminar-rethinking-data-use-in-large-language-models/
LOCATION:Wu and Chen Auditorium (Room 101)\, Levine Hall\, 3330 Walnut Street\, Philadelphia\, PA\, 19104\, United States
ORGANIZER;CN="Computer and Information Science":MAILTO:cherylh@cis.upenn.edu
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20240209T083000
DTEND;TZID=America/New_York:20240209T150000
DTSTAMP:20260404T085842
CREATED:20240201T155601Z
LAST-MODIFIED:20240201T155601Z
UID:10007844-1707467400-1707490800@seasevents.nmsdev7.com
SUMMARY:Women in Data Science @ Penn
DESCRIPTION:The Wharton School and Penn Engineering are proud to host the fifth annual Women in Data Science (WiDS) @ Penn Conference on February 8-9\, 2024\, on the University of Pennsylvania’s campus. A celebrated interdisciplinary event\, WiDS @ Penn welcomes academic\, industry\, and student speakers from across the data science landscape to celebrate its diversity\, both in subject matter and personnel.
URL:https://seasevents.nmsdev7.com/event/women-in-data-science-penn/
LOCATION:Jon M. Huntsman Hall\, 3730 Walnut Street\, Philadelphia\, PA\, 19104\, United States
CATEGORIES:Conference
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20240209T103000
DTEND;TZID=America/New_York:20240209T114500
DTSTAMP:20260404T085842
CREATED:20231120T162119Z
LAST-MODIFIED:20231120T162119Z
UID:10007762-1707474600-1707479100@seasevents.nmsdev7.com
SUMMARY:Spring 2024 GRASP on Robotics: Qixing Huang\, University of Texas at Austin\, "Geometric Regularizations for 3D Shape Generation"
DESCRIPTION:This is a hybrid event with in-person attendance in Wu and Chen and virtual attendance on Zoom. \nABSTRACT\nGenerative models\, which map a latent parameter space to instances in an ambient space\, enjoy various applications in 3D Vision and related domains. A standard scheme of these models is probabilistic\, which aligns the induced ambient distribution of a generative model from a prior distribution of the latent space with the empirical ambient distribution of training instances. While this paradigm has proven to be quite successful on images\, its current applications in 3D generation encounter fundamental challenges in the limited training data and generalization behavior. The key difference between image generation and shape generation is that 3D shapes possess various priors in geometry\, topology\, and physical properties. Existing probabilistic 3D generative approaches do not preserve these desired properties\, resulting in synthesized shapes with various types of distortions. In this talk\, I will discuss recent work that seeks to establish a novel geometric framework for learning shape generators. The key idea is to model various geometric\, physical\, and topological priors of 3D shapes as suitable regularization losses by developing computational tools in differential geometry and computational topology. We will discuss the applications in deformable shape generation\, latent space design\, joint shape matching\, and 3D man-made shape generation.
URL:https://seasevents.nmsdev7.com/event/spring-2024-grasp-on-robotics-qixing-huang-university-of-texas-at-austin-geometric-regularizations-for-3d-shape-generation/
LOCATION:Wu and Chen Auditorium (Room 101)\, Levine Hall\, 3330 Walnut Street\, Philadelphia\, PA\, 19104\, United States
CATEGORIES:Seminar
ORGANIZER;CN="General Robotics%2C Automation%2C Sensing and Perception (GRASP) Lab":MAILTO:grasplab@seas.upenn.edu
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20240209T140000
DTEND;TZID=America/New_York:20240209T150000
DTSTAMP:20260404T085842
CREATED:20240130T141449Z
LAST-MODIFIED:20240130T141449Z
UID:10007835-1707487200-1707490800@seasevents.nmsdev7.com
SUMMARY:PICS Colloquium: “Wall-models of turbulent flows via scientific multi-agent reinforcement learning”
DESCRIPTION:The predictive capabilities of turbulent flow simulations\, critical for aerodynamic design and weather prediction\, hinge on the choice of turbulence models. The abundance of data from experiments and simulations and the advent of machine learning have provided a boost to turbulence modeling efforts. However\, simulations of turbulent flows remain hindered by the inability of heuristics and supervised learning to model the near-wall dynamics. We address this challenge by introducing scientific multi-agent reinforcement learning (SciMARL) for the discovery of wall models for large-eddy simulations (LES). In SciMARL\, discretization points act also as cooperating agents that learn to supply the LES closure model. The agents self-learn using limited data and generalize to higher Reynolds numbers in reproducing key flow quantities. We test the discovered wall model to canonical flat plate boundary layers\, which shows good predictable capabilities outside the Reynolds numbers used to train the model. We will discuss extensions to this model for flows with pressure-gradient effects.
URL:https://seasevents.nmsdev7.com/event/pics-colloquium-wall-models-of-turbulent-flows-via-scientific-multi-agent-reinforcement-learning/
LOCATION:PICS Conference Room 534 – A Wing \, 5th Floor\, 3401 Walnut Street\, Philadelphia\, PA\, 19104\, United States
CATEGORIES:Colloquium
ORGANIZER;CN="Penn Institute for Computational Science (PICS)":MAILTO:dkparks@seas.upenn.edu
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20240212T110000
DTEND;TZID=America/New_York:20240212T120000
DTSTAMP:20260404T085842
CREATED:20240201T134202Z
LAST-MODIFIED:20240201T134202Z
UID:10007836-1707735600-1707739200@seasevents.nmsdev7.com
SUMMARY:ESE Spring Seminar - "Physics-inspired Machine Learning"
DESCRIPTION:Combining physics with machine learning is a rapidly growing field of research. Thereby\, most work focuses on leveraging machine learning methods to solve problems in physics. Here\, however\, we focus on the converse\, i.e.\, physics-inspired machine learning\, which can be described as incorporating structure from physical systems into machine learning methods to obtain models with better inductive biases. More concretely\, we propose several physics-inspired deep learning architectures for sequence modelling based on nonlinear coupled oscillators\, Hamiltonian systems and multi-scale dynamical systems. The proposed architectures tackle central problems in the field of recurrent sequence modeling\, namely the vanishing and exploding gradients problem as well as the issue of insufficient expressive power. Moreover\, we discuss physics-inspired learning on graphs\, wherein the dynamics of the message-passing propagation are derived from physical systems. We further prove that these methods mitigate the over-smoothing issue\, thereby enabling the construction of deep graph neural networks (GNNs). We extensively test all proposed methods on a variety of versatile synthetic and real-world datasets\, ranging from image recognition\, speech recognition\, natural language processing (NLP)\, medical applications\, and scientific computing for sequence models\, to citation networks\, computational chemistry applications\, and networks of articles and websites for graph learning models. Finally\, we show how to leverage physics-based inductive biases of physics-inspired machine learning methods to solve problems in the physical sciences.
URL:https://seasevents.nmsdev7.com/event/ese-spring-seminar-tbd/
LOCATION:Glandt Forum\, Singh Center for Nanotechnology\, 3205 Walnut Street\, Philadelphia\, PA\, 19104\, United States
CATEGORIES:Colloquium
ORGANIZER;CN="Electrical and Systems Engineering":MAILTO:eseevents@seas.upenn.edu
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20240212T130000
DTEND;TZID=America/New_York:20240212T150000
DTSTAMP:20260404T085842
CREATED:20240112T192252Z
LAST-MODIFIED:20240112T192252Z
UID:10007801-1707742800-1707750000@seasevents.nmsdev7.com
SUMMARY:BE Doctoral Dissertation Defense: "Computational imaging and multiomic biomarkers for precision medicine: characterizing heterogeneity in lung cancer" (Apurva Singh)
DESCRIPTION:The Department of Bioengineering at the University of Pennsylvania and Dr. Despina Kontos are pleased to announce the Doctoral Dissertation Defense of Apurva Singh.\n\nTitle:  “Computational imaging and multiomic biomarkers for precision medicine: characterizing heterogeneity in lung cancer”\nDate: February 12\, 2024\nTime: 1:00 PM\nLocation:  John Morgan Building\, Class of 62 auditorium\n\nZoom link\n\nThe public is welcome to attend.
URL:https://seasevents.nmsdev7.com/event/be-doctoral-dissertation-defense-computational-imaging-and-multiomic-biomarkers-for-precision-medicine-characterizing-heterogeneity-in-lung-cancer-apurva-singh/
LOCATION:Class of 62 Auditorium\, John Morgan Building\, 3620 Hamilton Walk\, Philadelphia\, PA\, 19104
CATEGORIES:Doctoral,Graduate,Student,Dissertation or Thesis Defense
ORGANIZER;CN="Bioengineering":MAILTO:be@seas.upenn.edu
END:VEVENT
END:VCALENDAR