Deep James-Stein Neural Networks For Brain-Computer Interfaces

Marko Angjelichinoski; Mohammadreza Soltani; John S. Choi; Bijan Pesaran; Vahid Tarokh

ICASSP 2020accepted0 citations

Deep James-Stein Neural Networks For Brain-Computer Interfaces

Marko Angjelichinoski, Mohammadreza Soltani, John S. Choi, Bijan Pesaran, Vahid Tarokh

Abstract

Nonparametric regression has proven to be successful in extracting features from limited data in neurological applications. However, due to data scarcity, most brain-computer interfaces still rely on linear classifiers. This work leverages the robustness of the James-Stein theorem in nonparametric regression to harness the potentials of deep learning and foster its successful application in neural engineering with small data sets. We propose a novel method that combines James-Stein regression for feature extraction, and deep neural network for decoding; we refer to the architecture as deep James-Stein neural network (DJSNN). We apply the DJSNN to decode eye movement goals in a memory-guided visual saccades to one of eight target locations. The results demonstrate that the DJSNN outperforms existing methods by a substantial margin, especially at deep cortical sites.

BibTeX

@inproceedings{icassp2020_deepjamessteinne,
  title = {Deep James-Stein Neural Networks For Brain-Computer Interfaces},
  author = {Marko Angjelichinoski and Mohammadreza Soltani and John S. Choi and Bijan Pesaran and Vahid Tarokh},
  booktitle = {ICASSP 2020},
  year = {2020}
}