TY - GEN
T1 - EEGNAS
T2 - 1st International Workshop on Human Brain and Artificial Intelligence, HBAI 2019, held in conjunction with the 28th International Joint Conference on Artificial Intelligence, IJCAI 2019
AU - Rapaport, Elad
AU - Shriki, Oren
AU - Puzis, Rami
N1 - Publisher Copyright:
© 2019, Springer Nature Singapore Pte Ltd.
PY - 2019/1/1
Y1 - 2019/1/1
N2 - EEG, Electroencephalography, is the acquisition and decoding of electric brain signals. The data acquired from EEG scans can be put to use in many fields, including seizure prediction, treatment of mental illness, brain-computer interfaces (BCIs) and more. Recent advances in deep learning (DL) in fields of image classification and natural language processing have motivated researchers to apply DL for classification of EEG signals as well. One major caveat in DL is the amount of human effort and expertise required for the development of efficient and effective neural network architectures. Neural architecture search algorithms are used to automatically find good enough neural network architectures for a problem and dataset at hand. In this research, we employ genetic algorithms for optimizing neural network architectures for multiple tasks related to EEG processing while addressing two unique challenges related to EEG: (1) small amounts of labeled EEG data per subject, and (2) high diversity of EEG signal patterns across subjects. Neural network architectures produced during this study successfully compete with state of the art architectures published in the literature. Particularly successful are architectures optimized for all (human) subjects, with evolution and training performed on a mixed dataset including all subjects’ data.
AB - EEG, Electroencephalography, is the acquisition and decoding of electric brain signals. The data acquired from EEG scans can be put to use in many fields, including seizure prediction, treatment of mental illness, brain-computer interfaces (BCIs) and more. Recent advances in deep learning (DL) in fields of image classification and natural language processing have motivated researchers to apply DL for classification of EEG signals as well. One major caveat in DL is the amount of human effort and expertise required for the development of efficient and effective neural network architectures. Neural architecture search algorithms are used to automatically find good enough neural network architectures for a problem and dataset at hand. In this research, we employ genetic algorithms for optimizing neural network architectures for multiple tasks related to EEG processing while addressing two unique challenges related to EEG: (1) small amounts of labeled EEG data per subject, and (2) high diversity of EEG signal patterns across subjects. Neural network architectures produced during this study successfully compete with state of the art architectures published in the literature. Particularly successful are architectures optimized for all (human) subjects, with evolution and training performed on a mixed dataset including all subjects’ data.
KW - EEG
KW - Neural architecture search
KW - Time series
UR - http://www.scopus.com/inward/record.url?scp=85076955405&partnerID=8YFLogxK
U2 - 10.1007/978-981-15-1398-5_1
DO - 10.1007/978-981-15-1398-5_1
M3 - Conference contribution
AN - SCOPUS:85076955405
SN - 9789811513978
T3 - Communications in Computer and Information Science
SP - 3
EP - 20
BT - Human Brain and Artificial Intelligence - 1st International Workshop, HBAI 2019, held in Conjunction with IJCAI 2019, Revised Selected Papers
A2 - Zeng, An
A2 - Pan, Dan
A2 - Hao, Tianyong
A2 - Zhang, Daoqiang
A2 - Shi, Yiyu
A2 - Song, Xiaowei
PB - Springer
Y2 - 12 August 2019 through 12 August 2019
ER -