EEG has been shown to be an interesting tool for a number of intensive care applications. However its potential remains partially untapped because human interpretation is not always adapted to long continuous records. This talk will present some of the ongoing approaches we are developing as part of my PhD work for automated analysis of intensive care EEG using machine learning.
First I will present a simple proof of concept of the use of deep networks on raw EEG samples for a different application: supervised sleep scoring using convolutional networks. I will then briefly delve into different architectural developments using recurrent networks. Finally I will talk about ongoing work on unsupervised approaches using joint clustering and feature learning algorithms trained end to end, which goal is to leverage large unlabeled EEG databases.
Wednesday 30 November 2016, 16:30 - 17:30 h
Building Carré - room CR 3.022