Connectionists: Post-Doctoral position at INRIA, Nancy, France

[Laurent Bougrain]

[Apologies for cross-posting]
-----------------------------
One year post-doctoral position in the INRIA-Cortex research project (http://cortex.loria.fr), Nancy, France

Main topic :

Brain-Computer Interface


Scientific context :

Brain-computer interface (BCI) system is a potentially powerful new communication and control option for those with severe motor 
disabilities. BCI system translates brain-activity into commands for a computer or other devices. In other words, a BCI allows users to act on 
their environment by using only brain-activity [1]. The success of this approach depends on close and productive interaction of scientists, 
engineers, and clinicians from many different disciplines and requires recognition and attention to a number of crucial issues. This offer is 
designed to foster such interdisciplinary interactions and thereby promote the development of BCI systems of practical value to people with 
disabilities using a non-invasive approach. Electroencephalography (EEG) is the most studied potential non-invasive interface, mainly due to its 
fine temporal resolution, ease of use, portability and low set-up cost. Unfortunately, non-invasive implants produce poor signal resolution 
because the skull dampens signals, dispersing and blurring the electromagnetic waves created by the neurons. Although the waves can 
still be detected it is more difficult to determine the area of the brain that created them or the actions of individual neurons. But as 
well as the technology's susceptibility to noise, another substantial barrier to using EEG as a brain-computer interface is the extensive 
training required before users can work the technology. Patterns of P300 waves are generated involuntarily (stimulus-feedback) when people see 
something they recognize and may allow BCIs to decode categories of thoughts without training patients first.
The Cortex project-team challenge is to develop neural networks to understand information processing in the brain and design numerical 
distributed and adaptive algorithms in interaction with biology and medical science. The project has recently bought a 32-channels high 
definition EEG/ERP amplifier by A.N.T. and wishes to use its experience on EEG signal analysis using neural networks to achieve this challenge. 
The candidate will come and reinforce this strategic goal.

Description of the post-doc activities :

The candidate will use is experience on ERP analysis to define an experimental protocol for healthy persons to collect measures on which a 
P300-based BCI system will be trained. Several classification techniques [2] will be compared including spatio-temporal artificial neural 
networks [3] to obtain high classification accuracy. The effect of different electrode configurations on classification accuracy will be 
also tested.

Applicant's required skills :

The Ph.D has to have strong knowledge in signal analysis and be familiar with EEG/ERP analysis. Basis knowledge in neurophysiology or in 
cognitive science will be appreciated. Experience using A.N.T. Amplifier will be also appreciated. The thesis defense should be RECENT (after the 
1st of may 2006).


To apply for, please send a CV and a covering letter to :
http://www.talentsplace.com/syndication1/inria/ukpostdoc/details.html?id=PNGFK026203F3VBQB6G68LOE1&LOV5=4508&LOV6=4513&LG=EN&Resultsperpage=20&nPostingID=1168&nPostingTargetID=3219&option=52&sort=DESC&nDepartmentID=19
Reference letters should be send directly to : bougrain at loria.fr

DEADLINE : 15 April 2007

---------------------------------------------------------

Bibliography :
[1] Wolpaw J.R. et al. Brain-computer interfaces for communication and control. Clinical Neurophysiology,
113:767-791 (2002).
[2] Lotte F., Congedo M., Lécuyer A., Lamarche F., Arnaldi B., "A Review of Classification Algorithms for
EEG-based Brain-Computer Interfaces", Journal of Neural Engineering, 4, R1-R13, (2007).
[3] Neji Ben Salem Z., Bougrain L., Alexandre F. Spatio-Temporal and Complex-Valued Models based on SOM
map applied to Speech Recognition. Workshop on Complex valued neural networks and neuro-computing: novel
methods, applications and implementations. Twentieth International Joint Conference on Artificial Intelligence -
IJCAI (2007)