Today, we would like to introduce you (drumroll, please) Dr Alex Gramfort, our next confirmed speaker at Brainhack Donostia 2020! If you have ever used Scikit Learn, you will probably recognise him as one of the core developers of this widely used machine learning Python library. But, he was also behind the creation of MNE, yet another open-source Python package for human neurophysiological data. Here, he will be talking about how our understanding of neurophysiological data has changed over the last few decades, and how recent advances in machine learning and deep learning are helping us to better understand EEG signals.
A bit about Dr Gramfort
Dr Gramfort is a senior researcher at INRIA, in France, and was an Assistant Professor at Telecom ParisTech, Université Paris-Saclay, in the image and signal processing department from 2012 to 2017. He is also affiliated with the Neurospin imaging center at CEA Saclay. His fields of expertise are signal and image processing, statistical machine learning, and scientific computing applied primarily to functional brain imaging data (EEG, MEG, fMRI). His work is strongly interdisciplinary, lying at the intersection of physics, computer science, software engineering, and neuroscience. He has co-authored more than 30 journal articles and 50 conference papers since 2009 and has received a number of awards. Dr Gramfort is deeply committed to open-source software development. He is a core developer of the Scikit-Learn machine learning software (http://scikit-learn.org) which is heavily used both in industry and in academic research. He is at the origin and the leader of the development of the MNE-Python software (https://mne.tools) now used and developed across many labs worldwide.
There’s a bit more about Alex’s talk in Brainhack Donostia in his abstract below!
Understanding how the brain works in healthy and pathological conditions is considered one of the major challenges for the 21st century. After the first electroencephalography (EEG) measurements in 1929, the ’90s was the birth of modern functional brain imaging with the first functional MRI (fMRI) and full head magnetoencephalography (MEG) system. By offering noninvasively unique insights into the living brain, imaging has revolutionized both clinical and cognitive neuroscience in the last twenty years. After pioneering breakthroughs in physics and engineering, the field of neuroscience has started to explore how statistical machine learning can help to address new questions and reveal new insights on neural recordings. In this talk, I will balance educational material on general machine learning concepts and present recent research findings based on deep learning applied to EEG data. This talk will be followed by a hands-on session during which you will apply the concepts seen on sleep EEG data.