*********************************
There is now a CONTENT FREEZE for Mercury while we switch to a new platform. It began on Friday, March 10 at 6pm and will end on Wednesday, March 15 at noon. No new content can be created during this time, but all material in the system as of the beginning of the freeze will be migrated to the new platform, including users and groups. Functionally the new site is identical to the old one. webteam@gatech.edu
*********************************
Title: On the Interplay between Brain-Computer Interfaces and Machine Learning Algorithms: A Systems Perspective
Committee:
Dr. Raupathy Sivakumar, ECE, Chair , Advisor
Dr. Faramarz Fekri, ECE
Dr. Chuanyi Ji, ECE
Dr. Douglas Blough, ECE
Dr. Karthik Ramachandran, Scheller COB
Abstract: Today, computer algorithms use traditional human-computer interfaces (e.g., keyboard, mouse, gestures, etc.), to interact with and extend human capabilities across all knowledge domains, allowing them to make complex decisions underpinned by massive datasets and machine learning. Machine learning has seen remarkable success in the past decade in obtaining deep insights and recognizing unknown patterns in complex data sets, in part by emulating how the brain performs certain computations. As we increase our understanding of the human brain, brain-computer interfaces can benefit from the power of machine learning, both as an underlying model of how the brain performs computations and as a tool for processing high-dimensional brain recordings. The technology (machine learning) has come full circle and is being applied back to understanding the brain and any electric residues of the brain activity over the scalp (EEG). Similarly, domains such as natural language processing, machine translation, and scene understanding remain beyond the scope of true machine learning algorithms and require human participation to be solved. In this work, we investigate the interplay between brain-computer interfaces and machine learning through the lens of end-user usability. Specifically, we propose the systems and algorithms to enable synergistic and user-friendly integration between computers (machine learning) and the human brain (brain-computer interfaces). In this context, we provide our research contributions in two inter-related aspects by, (i) applying machine learning to solve challenges with EEG-based BCIs, and (ii) enabling human-assisted machine learning with EEG-based feedback loop.
