• Englishen
  • Françaisfr
  • thumbnail of 2017 Koerding-3Neuroscience Seminar Series:
    Friday, December  1st, 2017 , 11:30 am, Salle des conférences (3rd Floor), Centre Universitaire des Saints-Pères, 45 rue des Saints-Pères, 75006 Paris

    Konrad Koerding

    Professor – Department of Bioengineering and Department of Neuroscience

    University of Pennsylvania




    Rethinking the role of machine learning in neuroscience »



    The goal of much of computational biology is to numerically describe data from a system, but also to find ways of fixing it and to understand a system’s objectives, algorithms, and mechanisms. Here we will argue that, regardless the objective, machine learning should be a central contribution to progress in every flavor of biomedical science. Machine learning can typically better describe the data. In doing so it can also provide a benchmark for any other way of describing the data. Using examples from neuroscience we discuss how better performance matters for decoding models and how having a benchmark affects encoding models. Similar issues matter in medicine. As biomedical science evolves, machine learning is morphing into a critical tool across the full spectrum of scientific questions. 



    Eef Joosten: pointer1313@gmail.com

    Cecile Issard: cecile.issard@etu.parisdescartes.fr