Login

Spring Workshop on Physics of Data

6–8 Apr 2022
Istituto Veneto di Scienze Lettere ed Arti, Venezia
Europe/Rome timezone

Session

Machine Learning, Data Science & Interdisciplinary applications

6 Apr 2022, 14:45
Istituto Veneto di Scienze Lettere ed Arti, Venezia

Istituto Veneto di Scienze Lettere ed Arti, Venezia

Conveners

Machine Learning, Data Science & Interdisciplinary applications

  • Samir Suweiss (University of Padova)

Machine Learning, Data Science & Interdisciplinary applications

  • Samir Suweiss (University of Padova)

Presentation materials

There are no materials yet.

  1. 4. Timescales of neural activity, their inference and relevance.
    Anna Levina (University of Tuebingen)
    06/04/2022, 14:45

    Timescales characterize how fast the observables change in time. In neuro science, they can be estimated from the measured activity and can be used, for example, as a signature of the memory trace in the activations. Inferring the
    timescales seems to be an easy task; however, I will show you how the timescales are subject to a statistical bias that is impossible to remove by a simple...

    Go to contribution page
  2. 5. Physics of data for social impact
    Elisa Omodei (Central European University)
    06/04/2022, 15:30

    In a rapidly changing world, facing an increasing number of socioeconomic, health and environmental crises, physics of data and complex systems can help us to assess and quantify
    vulnerabilities, and to monitor and achieve the UN Sustainable Development Goals. In this talk, I will provide an overview of the main areas of applications where physics of data and
    complex systems has shown its...

    Go to contribution page
  3. 6. Failure and success of the spectral bias prediction for Kernel Ridge Regression: the case of low-dimensional data
    Umberto Tomasini (EPFL)
    06/04/2022, 16:45
  4. 7. Language-dependent model-based deep reinforcement learning
    Nicola Dainese (Aalto University)
    06/04/2022, 17:00
  5. 8. Rethinking the Geometry of Machine Learning: “Physics of Data” Five Years Later
    Jeff Byers (Naval Research Laboratory)
    06/04/2022, 17:15

    In physics the data that is acquired in experiments are highly-controlled and often taken with specific goals in mind. However, the notion of a “Physics of Data” is about using mathematical tools developed in physics to understand data acquired in more open-ended and uncontrolled environments. As the data acquisition process becomes more opaque and distant from any particular purpose, we have...

    Go to contribution page
Building timetable...