Page tree

Versions Compared


  • This line was added.
  • This line was removed.
  • Formatting was changed.


Colloquium on Digital Transformation Science

  • May 613, 3 pm CT

    Bringing Social Distancing to Light: Architectural Interventions for COVID-19 Containment

    Stefana Parascho, Assistant Professor of Architecture, Princeton University
    Corina Tarnita, Associate Professor of Ecology & Evolutionary Biology, Princeton University

    Graceful AI: Backward-Compatibility, Positive-Congruent Training, and the Search for Desirable Behavior of Deep Neural Networks

    Vice President of Applied Science, Amazon Web Services, Professor of Computer Science, UCLA


    With the spread of COVID-19, social distancing has become an integral part of our everyday lives. Worldwide, efforts are focused on identifying ways to reopen public spaces, restart businesses, and reintroduce physical togetherness. We believe that architecture plays a key role in the return to a healthy public life by providing a means for controlling distances between people. Making use of computational processing power and data accessibility, we investigate how we can promote healthy and efficient movement through public spaces. Our approach is dynamic, to easily accommodate developing requirements and programmatic changes within these spaces.

    In this talk, we will present previous work focusing on collective behavior and architectural installations and our vision of strategy to address social distancing challenges: a physical intervention system based on light projections that provides direct real-time information about safe trajectories and movement behavior for pedestrians. To execute this vision, we take an approach grounded in computational architectural design, but also draw insights from collective behaviors in biological systems.

    Stefana Parascho, Assistant Professor of Architecture at Princeton University, is an architect with teaching and research in the field of computational design and robotic fabrication. Prior to joining Princeton University, she completed her doctorate at ETH Zurich and her architectural studies at the University of Stuttgart. Her research interest lies at the intersection of design, structure, and fabrication, with a focus on fabrication-informed design. She explores computational design methods and their potential role for architectural construction, ranging from agent-based models to mathematical optimization. Her goal is to strengthen the connection between design, structure, and fabrication and the interdisciplinary nature of architectural design through the development of accessible computational design tools.

    Corina Tarnita is an Associate Professor in Ecology and Evolutionary Biology and the Director of the Program in Environmental Studies at Princeton University. Previously, she was a Junior Fellow at the Harvard Society of Fellows (2010-2012). She obtained her B.A. (2006), M.A. (2008), and PhD (2009) in Mathematics from Harvard University. She is an ESA Early Career Fellow, a Kavli Frontiers of Science Fellow of the National Academy of Sciences, and an Alfred P. Sloan Research Fellow. Her work is centered around the emergence of complex behavior out of simple interactions, across spatial and temporal scalesAs machine learning-based decision systems improve rapidly, we are discovering that it is no longer enough for them to perform well on their own. They should also behave nicely towards their predecessors and peers. More nuanced demands beyond accuracy now drive the learning process, including robustness, explainability, transparency, fairness, and now also compatibility and regression minimization. We call this “Graceful AI,'’ because in 2021, when we replace an old trained classifier with a new one, we should expect a peaceful transfer of decision powers. Today, a new model can introduce errors that the old model did not make, despite significantly improving average performance. Such “regression” can break post-processing pipelines, or cause the need to reprocess large amounts of data. How can we train machine learning models to not only minimize the average error, but also minimize “regression”? Can we design and train new learning-based models in a manner that is compatible with previous ones, so that it is not necessary to re-process any data? These problems are prototypical of the nascent field of cross-model compatibility in representation learning. I will describe the first approach to Backward-Compatible Training (BCT), introduced at the last Conference on Computer Vision and Pattern Recognition (CVPR), and an initial solution to the problem of Positive-Congruent Training (PC-Training), a first step towards “regression constrained” learning, to appear at the next CVPR. Along the way, I will also introduce methodological innovations that enable full-network fine-tuning by solving a linear-quadratic optimization. Such Linear-Quadratic Fine-Tuning (LQF, also to appear at the next CVPR) achieves performance equivalent to non-linear fine-tuning, and superior in the low-data regime, while allowing easy incorporation of convex constraints.

    Stefano Soatto is Vice President of Applied Science at Amazon Web Services AI, where he oversees research for AI Applications including vision (Custom Labels, Lookout4Vision), speech (Amazon Transcribe), natural language (Amazon Comprehend, Amazon Lex, Amazon Kendra, Amazon Translate), Document Understanding (Amazon Textract), time series analysis (Amazon Forecast, Lookout4Metrics, Lookout4Equipment), personalization (Amazon Personalize) and others in the works. He is also a Professor of Computer Science at UCLA and founding director of the UCLA Vision Lab.

Quick Links: DTI Webpage


Information on Call for Proposals

Proposal Matchmaking DTI Training Materials Overview (password protected)

C3 Administration (password protected)

Have Questions? Please contact one of us:

Recent space activity

Recently Updated
typespage, comment, blogpost

Space contributors