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.

Assessing pattern recognition performance of neuronal cultures through accurate simulation / Lagani G.; Mazziotti R.; Falchi F.; Gennaro C.; Cicchini G.M.; Pizzorusso T.; Cremisi F.; Amato G.. - ELETTRONICO. - 2021-:(2021), pp. 726-729. (Intervento presentato al convegno 10th International IEEE/EMBS Conference on Neural Engineering, NER 2021 tenutosi a ita nel 2021) [10.1109/NER49283.2021.9441166].

Assessing pattern recognition performance of neuronal cultures through accurate simulation

Mazziotti R.;Falchi F.;Cicchini G. M.;Pizzorusso T.;
2021

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.
2021
International IEEE/EMBS Conference on Neural Engineering, NER
10th International IEEE/EMBS Conference on Neural Engineering, NER 2021
ita
2021
Lagani G.; Mazziotti R.; Falchi F.; Gennaro C.; Cicchini G.M.; Pizzorusso T.; Cremisi F.; Amato G.
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificatore per citare o creare un link a questa risorsa: https://hdl.handle.net/2158/1317091
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 4
  • ???jsp.display-item.citation.isi??? 2
social impact