Data-Driven Science and Engineering Seminars

Data-Driven Science and Engineering Seminars

AI Institute in Dynamic Systems

Our mission is to develop the next generation of advanced machine learning tools for controlling complex physical systems by discovering physically interpretable and physics-constrained data-driven models through optimal sensor selection and placement. Our work is anchored by a common task framework that evaluates the performance of machine learning algorithms, architectures, and optimization schemes for the diverse tasks required in engineering applications. We will push beyond the boundaries of modern techniques by closing the loop between data collection, control, and modeling, creating a unique and cross-disciplinary architecture for learning physically interpretable and physics constrained models of complex dynamic systems from time series data.

Speakers
Community
AI Institute in Dynamic Systems
AI Institute in Dynamic Systems
University of California, Los Angeles

Extreme Aerodynamics: Flow Analysis and Control for Highly Gusty Conditions

Kunihiko Taira, University of California, Los Angeles
University of Vienna

An intrinsic neuronal manifold underlies brain-wide hierarchical organization of behavior in C. elegans

Charles Fieseler, University of Vienna
Pacific Northwest National Laboratory

Multifidelity, domain decomposition, and stacking for improving training for physics-informed networks

Amanda Howard, Pacific Northwest National Laboratory
University of California, Berkeley

Advances in Advancing Interfaces: The Mathematics of Manufacturing of Industrial Foams, Fluidic Devices, and Automobile Painting

James Sethian, University of California, Berkeley
Universidade de Vigo

Learning the shape: streamlining data needs in 2D irregular contour parameterization

Ana Larrañaga Janeiro, CINTECX
University of Washington

Statistical mechanics lessons for data-driven methods

Andrei A. Klishin, University of Hawaiʻi at Mānoa
University of Twente

Data Efficient, Robust, and Interpretable Deep Reinforcement Learning for Robotics and Dynamical Systems

Nicolò Botteghi, University of Twente
United States Naval Research Laboratory

Enabling Model Reduction of Meshless Nonlocal Methods via Modal Reference Spaces

Steven Rodriguez, United States Naval Research Laboratory
Iowa State University

Multi-scale Modeling and Simulations using Digital Twins

Adarsh Krishnamurthy, Iowa State University