Deep Learning

Blind in vivo localization of microelectrode arrays via functional correlation patterns in the mouse hippocampus

We developed a learning-based automatic localizer to accurately identify hippocampal sublayer in mice from high-density extracellular recordings by aligning neural manifolds across sessions and animals.

Embedding Decomposition for Artifacts Removal in EEG Signals

DeepSeparator is a deep learning framework designed to separate neural signals from artifacts in EEG recordings and reconstruct clean signals.