| Paper: | PS-2B.58 | ||
| Session: | Poster Session 2B | ||
| Location: | H Fläche 1.OG | ||
| Session Time: | Sunday, September 15, 17:15 - 20:15 | ||
| Presentation Time: | Sunday, September 15, 17:15 - 20:15 | ||
| Presentation: | Poster | ||
| Publication: | 2019 Conference on Cognitive Computational Neuroscience, 13-16 September 2019, Berlin, Germany | ||
| Paper Title: | Pattern recognition of deep and superficial layers of the macaque brain using large-scale local field potentials | ||
| Manuscript: | Click here to view manuscript | ||
| License: |  This work is licensed under a Creative Commons Attribution 3.0 Unported License. |
||
| DOI: | https://doi.org/10.32470/CCN.2019.1159-0 | ||
| Authors: | Omar Costilla-Reyes, Andre M Bastos, Earl K Miller, Massachusetts Institute of Technology, United States | ||
| Abstract: | Robust identification of cortical deep (layers 5 and 6) and superficial (layer 2 and 3) layers of the brain based on neurophysiological recordings is a challenging and unsolved problem in neuroscience. We still lack a complete understanding of the fine-grained neural computations in these layers. In this paper, we introduce a machine learning approach to identify deep and superficial layers patterns. We use multilaminar probes to capture local field potentials (LFP) data in cortical layers of the macaque brain. Here we present experimental modeling results of deep and superficial layers in the prefrontal cortex (PFC) and visual area four (V4) during a delayed match to sample task. Recordings spanned all six cortical layers simultaneously over 10 experimental sessions in these 2 areas. Our experimental results demonstrate that an ensemble machine learning approach applied to the LFP data is able to provide robust levels of identification of the layers with an optimal f-score of 0.8 and 0.84 for areas V4 and PFC respectively in combined data of 10 experimental sessions and across two monkeys. | ||