Deep Learning and other Machine Learning and Signal Processing Methods for Analyzing EEG in BCI Paradigms

Workshop at the 2016 International Brain-Computer Interface (BCI) Meeting

Planned Presenters:

• Chuck Anderson, Colorado State University
• Elliott Forney, Colorado State University
• Dean Krusienski, Old Dominion University
• Yalda Shahriari, University of California, San Francisco
• Damien Coyle, University of Ulster

Abstract: Many advanced data analysis methods have been developed for EEG pattern recognition, but few have resulted in BCI performance that surpasses what is achieved with simple linear methods. The recent success of deep learning methods for difficult problems of image and speech recognition and similarities between such data and EEG signals suggest that deep learning might contribute to BCI advances. In this workshop, the deep learning framework will be introduced. Implementations in the Python programming language of some of the associated machine learning algorithms will be presented and demonstrated through applications to EEG signal classification in BCI paradigms.

Intended Audience: This workshop is intended for all who are curious about deep learning methods as mentioned in the popular press, and for engineers who have experience with deep learning methods and their application. A basic understanding of computer programming, especially in Python, will be helpful.

Learning Objectives: This workshop is designed to meet the following learning objectives.

1. Participants will learn about common methods for representing and analyzing EEG signals and about new approaches.

2. Participants with some experience in EEG signal classification will learn why deep learning is receiving so much attention in the recent research literature and popular press.

3. Participants will gain insights into how the deep learning framework might lead to increases in BCI reliability.