Séminaire CoNECT

Etienne Thoret (ILCB/PRISM/LIS/AMU) présente son projet de recherche dans le cadre de la nouvelle série de séminaires CONECT-core © ( ces séminaires sont ouverts à tous mais sont centrés sur les enjeux scientifiques et théoriques des membres de CoNECT)

‘Explainable AI for computational auditory neurosciences‘

Abstract

Machine learning and deep neural networks have been raised as compelling models to simulate a broad range of tasks on signals: from classification of sound events to the prediction of human physiological state from electrophysiological data. But what do we really understand about these models and how do they process the information they have been trained to process? As users, we often use them as tools without precisely understanding their mechanistic and representational underpinnings. In this talk, I’ll present recent works on how we can take part of these computational systems to answer fundamental research mysteries on auditory perception, speech production and cerebral processing. Beyond acoustics and sound perception, these techniques can find applications for the modeling of a variety of systems, including computational vision in robotics, haptics and clinical applications.

More info and zoom link @ https://framateam.org/int-marseille/channels/conect.