Cross Task Neural Architecture Search for EEG Signal Classifications

Abstract

Electroencephalograms (EEGs) are brain dynamics measured outside of the brain, which have been widely utilized in non-invasive brain-computer interface applications. Recently, various neural network approaches have been proposed to improve the accuracy of EEG signal recognition. However, these approaches severely rely on manually designed network structures for different tasks which normally are not sharing the same empirical design cross-task-wise. In this paper, we propose a cross-task neural architecture search (CTNAS-EEG) framework for EEG signal recognition, which can automatically design the network structure across tasks and improve the recognition accuracy of EEG signals. Specifically, a compatible search space for cross-task searching and an efficient constrained searching method is proposed to overcome challenges brought by EEG signals. By unifying structure search on different EEG tasks, this work is the first to explore and analyze the searched structure difference in crosstask-wise. Moreover, by introducing architecture search, this work is the first to analyze model performance by customizing model structure for each human subject. Detailed experimental results suggest that the proposed CTNAS-EEG could reach state-of-the-art performance on different EEG tasks, such as Motor Imagery (MI) and Emotion recognition. Extensive experiments and detailed analysis are provided as a good reference for follow-up researchers. We will release the source code 1 to contribute to the open source community.

Speech2EEG: Leveraging Pretrained Speech Model for EEG Signal Recognition

“…Other architectures, such as graph embedding [68] and long-short term memory (LSTM) [69], have also been proposed to recognize raw EEG signals. To determine the optimal architecture, recent work has also tried to search for the optimal network architecture for each subject using neural network search (NAS) algorithms [70].…”