Cross-Subject Data Splitting for Brain-to-Text Decoding

arXiv:2312.10987v3 Announce Type: replace
Abstract: Recent major milestones have successfully decoded non-invasive brain signals (e.g. functional Magnetic Resonance Imaging (fMRI) and electroencephalogram (EEG)) into natural language. Despite the progress in model design, how to split the datasets for training, validating, and testing still remains a matter of debate. Most of the prior researches applied subject-specific data splitting, where the decoding model is trained and evaluated per subject. Such splitting method poses challenges to the utilization efficiency of dataset as well …

abstract arxiv brain brain signals cs.cl data datasets decoding design eeg fmri functional imaging language major matter milestones model design natural natural language prior progress replace split testing text training type