| Title | Machine Learning for Neural Engineering Applications |
| Speaker | Dr. Justin Dauwels |
| Chair | Paulo Lisboa |
Abstract
This talk presents an overview of current research activities on machine learning methods for neural engineering applications. In a first application, we aim to diagnose Alzheimer’s disease (AD) from EEG signals. We will describe a variety of computational methods that we have developed to detect signatures of AD in EEG signals. In a second application, we analyze interictal intracranial EEG signals of epilepsy patients in order to detect the seizure focus. We will elaborate on our decision theoretic approach to infer the seizure focus from such EEG signals. We will also touch upon our parallel effort to develop nonlinear dynamical models of epileptic EEG. As a third application, we will outline our recently developed near-lossless compression methods for EEG signals.
Biography
Justin Dauwels is an Assistant Professor with School of Electrical & Electronic Engineering at Nanyang Technological University (NTU).
His research interests are in Bayesian statistics, iterative signal processing, and computational neuroscience. He enjoys working on real-world problems, often in collaboration with medical practitioners. He also tries to bring real-world problems into the classroom. Research from his team is featured at the Singapore Science Center and in the Straits Times.
Prior to joining NTU, Justin was a research scientist during 2008-2010 in the Stochastic Systems Group (SSG) at the Massachusetts Institute of Technology (MIT), led by Prof. Alan Willsky. He received postdoctoral training during 2006-2007 under the guidance of Prof. Shun-ichiAmari and Prof. Andrzej Cichocki at the RIKEN Brain Science Institute in Wako-shi, Japan.
He obtained a PhD degree in electrical engineering at the Swiss Polytechnical Institute of Technology (ETH) in Zurich in December 2005, supervised by Prof. Hans-Andrea Loeliger, and was a teaching and research assistant at the Signal and Information Processing Laboratory (ISI) of the Department of Information Technology and Electrical Engineering at ETH Zurich from 2000 to 2005. In 2000 he received the engineering physics degree from the University of Ghent.
He has been a JSPS postdoctoral fellow (2007), a BAEF fellow (2008), a Henri-Benedictus Fellow of the King Baudouin Foundation (2008), and a JSPS invited fellow (2010). He has received several best paper awards at conferences.