Deep Metric Learning with Locality Sensitive Angular Loss for Self-Correcting Source Separation of Neural Spiking Signals
This addresses the need for automated post-hoc cleaning and robust separation in neuroscience and neuroengineering, though it appears incremental as it builds on existing deep metric learning techniques.
The paper tackled the problem of errors in source separation algorithms for neural spiking signals by proposing a deep metric learning method with a novel loss function, which recovered original timestamps even under extreme noise conditions in high-density surface electromyography recordings.
Neurophysiological time series, such as electromyographic signal and intracortical recordings, are typically composed of many individual spiking sources, the recovery of which can give fundamental insights into the biological system of interest or provide neural information for man-machine interfaces. For this reason, source separation algorithms have become an increasingly important tool in neuroscience and neuroengineering. However, in noisy or highly multivariate recordings these decomposition techniques often make a large number of errors, which degrades human-machine interfacing applications and often requires costly post-hoc manual cleaning of the output label set of spike timestamps. To address both the need for automated post-hoc cleaning and robust separation filters we propose a methodology based on deep metric learning, using a novel loss function which maintains intra-class variance, creating a rich embedding space suitable for both label cleaning and the discovery of new activations. We then validate this method with an artificially corrupted label set based on source-separated high-density surface electromyography recordings, recovering the original timestamps even in extreme degrees of feature and class-dependent label noise. This approach enables a neural network to learn to accurately decode neurophysiological time series using any imperfect method of labelling the signal.