Decoding EEG and LFP signals using deep learning: Heading truenorth

Abstract

Deep learning technology is uniquely suited to analyse neu-rophysiological signals such as the electroencephalogram (EEG) and local field potentials (LFP) and promises to outperform traditional machine-learning based classification and feature extraction algorithms. Furthermore, novel cognitive com-puting platforms such as IBM's recently introduced neuro-morphic TrueNorth chip allow for deploying deep learning techniques in an ultra-low power environment with a mini-mum device footprint. Merging deep learning and TrueNorth technologies for real-Time analysis of brain-Activity data at the point of sensing will create the next generation of wear-ables at the intersection of neurobionics and artificial intel-ligence.