Psychology and Neuroscience Faculty Database
Psychology and Neuroscience
Arts & Sciences
Duke University

 HOME > Arts & Sciences > pn > Faculty    Search Help Login pdf version printable version 

Publications [#333740] of Geraldine Dawson

search PubMed.

Chapters in Books

  1. Li, Y; Murias, M; Major, S; Dawson, G; Dzirasa, K; Carin, L; Carlson, DE "Targeting EEG/LFP synchrony with neural nets."  Ed. Guyon, I; Luxburg, UV; Bengio, S; Wallach, HM; Fergus, R; Vishwanathan, SVN; Garnett, R January, 2017: 4621-4631.
    (last updated on 2024/03/28)

    Abstract:
    We consider the analysis of Electroencephalography (EEG) and Local Field Potential (LFP) datasets, which are "big" in terms of the size of recorded data but rarely have sufficient labels required to train complex models (e.g., conventional deep learning methods). Furthermore, in many scientific applications, the goal is to be able to understand the underlying features related to the classification, which prohibits the blind application of deep networks. This motivates the development of a new model based on parameterized convolutional filters guided by previous neuroscience research; the filters learn relevant frequency bands while targeting synchrony, which are frequency-specific power and phase correlations between electrodes. This results in a highly expressive convolutional neural network with only a few hundred parameters, applicable to smaller datasets. The proposed approach is demonstrated to yield competitive (often state-of-the-art) predictive performance during our empirical tests while yielding interpretable features. Furthermore, a Gaussian process adapter is developed to combine analysis over distinct electrode layouts, allowing the joint processing of multiple datasets to address overfitting and improve generalizability. Finally, it is demonstrated that the proposed framework effectively tracks neural dynamics on children in a clinical trial on Autism Spectrum Disorder.


Duke University * Arts & Sciences * Faculty * Staff * Grad * Postdocs * Reload * Login