Deep Learning for micro-Electrocorticographic ({\mu}ECoG) Data

TL;DR

This paper demonstrates that convolutional neural networks significantly improve decoding accuracy of micro-ECoG signals compared to traditional methods, highlighting deep learning's potential in brain-machine interfaces.

Contribution

It introduces a deep learning approach using ConvNets for {}ECoG data, outperforming traditional feature-based methods in neural signal decoding.

Findings

ConvNets achieved higher decoding accuracy than rLDA and FBCSP.

End-to-end training of ConvNets eliminates the need for predefined features.

Deep learning shows promise for {}ECoG-based brain-machine interfaces.

Abstract

Machine learning can extract information from neural recordings, e.g., surface EEG, ECoG and {\mu}ECoG, and therefore plays an important role in many research and clinical applications. Deep learning with artificial neural networks has recently seen increasing attention as a new approach in brain signal decoding. Here, we apply a deep learning approach using convolutional neural networks to {\mu}ECoG data obtained with a wireless, chronically implanted system in an ovine animal model. Regularized linear discriminant analysis (rLDA), a filter bank component spatial pattern (FBCSP) algorithm and convolutional neural networks (ConvNets) were applied to auditory evoked responses captured by {\mu}ECoG. We show that compared with rLDA and FBCSP, significantly higher decoding accuracy can be obtained by ConvNets trained in an end-to-end manner, i.e., without any predefined signal features. Deep learning thus proves a promising technique for {\mu}ECoG-based brain-machine interfacing applications.