Inter-Subject MEG Decoding for Visual Information with Hybrid Gated Recurrent Network

As an effective brain signal recording technique for neuroscience, magnetoencephalography (MEG) is widely used in cognitive research. However, due to the low signal-to-noise ratio and structural or functional variabilities of MEG signals between different subjects, conventional methods perform poorly decoding human responds. Inspired by deep recurrent network processing sequential data, we applied gated units processing. In paper, proposed a hybrid (HGRN) inter-subject visual decoding. Without need any information from test HGRN effectively distinguished evoked stimulations, face scrambled face. leave-one-out cross-validation experiments on sixteen our method achieved better performance than many existing methods. For more in-depth analysis, can be utilized extract spatial features temporal signals. These conformed previous studies which demonstrated practicality Consequently, model considered as new tool analyzing signal, significant research neuroscience.