Deep learning based feature extraction for prediction and interpretation of sharp-wave ripples

Abstract

Local field potential (LFP) deflections and oscillations define hippocampal sharp-wave ripples (SWR), one of the most synchronous events of the brain. SWR reflect firing and synaptic current sequences emerging from cognitively relevant neuronal ensembles. Current spectral methods fail to capture their mechanistic complexity, thus limiting progress. Here, we show how one-dimensional convolutional networks operating over high-density LFP hippocampal recordings allowed for automatic identification of SWR. When applied to ultra-dense hippocampus-wide recordings, we discovered physiologically relevant processes associated to the emergence of SWR, prompting for novel classification criteria. To gain interpretability, we developed a method to interrogate the operation of the artificial network. We found it relied in feature-based specialization, which permit identification of spatially segregated oscillations and deflections, as well as synchronous population firing. Thus, using deep learning based approaches may change the current heuristic for a better mechanistic interpretation of these relevant neurophysiological events.