[BIC-announce] MCIN Lecture - Today - Yannick Roy - Deep Learning for EEG

[Patrick Bermudez]

Join us today at 13:00 in the de Grandpré auditorium for a
presentation by Yannick Roy entitled:

"After reviewing more than 150 scientific papers on deep learning for
EEG here is what we've learned...".

In Yannick's own words, here is a description of the talk and his biography.

-------------
Description:
The use of deep learning for EEG data has increased exponentially over
the past couple of years and yet it is still hard to understand the
best practices. After reviewing 156 scientific papers between 2010 and
2018 across different domains such as sleep, epilepsy, brain-computer
interfaces, cognitive and affective monitoring, we've identified the
main trends in the field. Over 60 data items were extracted for each
study pertaining to 1) the data, 2) the preprocessing methodology, 3)
the DL design choices, 4) the results, and 5) the reproducibility of
the experiments. Additionally, we've tried to answer questions such as
"how much data is enough data for DL?" and "is deep learning better
than traditional machine learning?". Finally, we've come up with some
recommendations for researchers in the field.

Biography:
Yannick Roy is doing his PhD at Université de Montréal on
brain-computer interfaces (BCI) in the context of cognitive training.
He is also spearheading NeuroTechX – an international neurotech
community, as its executive director. He is an electrical engineer
with a background in computer science and he’s obsessed about
combining brain & tech. When he's not in his lab working on his
research, or engaging with neurotech enthusiasts, or teaching computer
science at ETS, he's probably training for a triathlon.
-------------