Exploring Deep Learning Models for EEG Neural Decoding
This work addresses the problem of decoding complex brain representations from EEG data for cognitive neuroscience researchers, though it is incremental as it applies existing deep learning methods to a new dataset.
The researchers tested whether deep learning models could decode high-level object features from EEG data, finding that while a state-of-the-art linear model failed, nearly all 15 deep learning models succeeded, demonstrating the necessity of non-linear approaches for this neural decoding task.
Neural decoding is an important method in cognitive neuroscience that aims to decode brain representations from recorded neural activity using a multivariate machine learning model. The THINGS initiative provides a large EEG dataset of 46 subjects watching rapidly shown images. Here, we test the feasibility of using this method for decoding high-level object features using recent deep learning models. We create a derivative dataset from this of living vs non-living entities test 15 different deep learning models with 5 different architectures and compare to a SOTA linear model. We show that the linear model is not able to solve the decoding task, while almost all the deep learning models are successful, suggesting that in some cases non-linear models are needed to decode neural representations. We also run a comparative study of the models' performance on individual object categories, and suggest how artificial neural networks can be used to study brain activity.