|
|
SEMINAR DETAILS |
|
Time: |
2:00 PM - 3:00 PM |
|
Place: |
133 Rosenau Hall Auditorium |
|
Speaker: |
Joelle Pineau, PhD |
|
Affiliation |
School of Computer Science
McGill University |
|
Title & Abstract: |
Adaptive Stimulation Design for the Treatment of Epilepsy
Electrical stimulation has recently emerged as a promising therapy for patients with medically intractable epilepsy. However little is known about the best stimulation patterns to use, such that we get maximal seizure reduction, while also minimizing long-term damage to the brain. The overall goal of this project is to automatically optimize a closed-loop strategy for the control of deep brain stimulation using reinforcement learning methods. In this talk I will present some of the key methodological challenges that must be addressed in order to automatically learn adaptive treatment strategies in this context. In particular I will discuss the use of ensemble methods to automatically detect seizures. I will also present initial results of applying reinforcement learning using in vitro models of epilepsy. Finally, I will discuss whether accurate seizure prediction is necessary to develop a successful treatment strategy. |
|
Contact : |
Tania Osborn (919) 966-7268 |
|
Notes: |
n/a |
|
|
Last updated March 05, 2008 |