Assessing Pattern Recognition Performance of Neuronal Cultures through Accurate Simulation
Abstract
Previous work has shown that it is possible to train neuronal cultures on Multi-Electrode Arrays (MEAs), to recognize very simple patterns. However, this work was mainly focused to demonstrate that it is possible to induce plasticity in cultures, rather than performing a rigorous assessment of their pattern recognition performance. In this paper, we address this gap by developing a methodology that allows us to assess the performance of neuronal cultures on a learning task. Specifically, we propose a digital model of the real cultured neuronal networks; we identify biologically plausible simulation parameters that allow us to reliably reproduce the behavior of real cultures; we use the simulated culture to perform handwritten digit recognition and rigorously evaluate its performance; we also show that it is possible to find improved simulation parameters for the specific task, which can guide the creation of real cultures.
Cite
@article{arxiv.2012.10355,
title = {Assessing Pattern Recognition Performance of Neuronal Cultures through Accurate Simulation},
author = {Gabriele Lagani and Raffaele Mazziotti and Fabrizio Falchi and Claudio Gennaro and Guido Marco Cicchini and Tommaso Pizzorusso and Federico Cremisi and Giuseppe Amato},
journal= {arXiv preprint arXiv:2012.10355},
year = {2021}
}
Comments
4 pages, 2 figures. Submitted to NER 2021 conference