EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Combination of Organic‐Based Reservoir Computing and Spiking Neuromorphic Systems for a Robust and Efficient Pattern Classification

Anna N. Matsukatova, Nikita V. Prudnikov, Vsevolod A. Kulagin, Silvia Battistoni, Anton A. Minnekhanov, Andrey D. Trofimov, Aleksandr A. Nesmelov, Sergey A. Zavyalov, Yulia N. Malakhova, Matteo Parmeggiani, Alberto Ballesio, Simone Luigi Marasso und 4 weitere

Advanced Intelligent Systems · 2023-06 · 5 (6)

DOI: 10.1002/aisy.202200407 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Advanced Intelligent Systems, 2023-03. Verfasst von Anna N. Matsukatova und 15 weiteren Autor:innen. Die Arbeit wurde bisher 68-mal zitiert (Crossref) und nennt 59 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Russian Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Nowadays, neuromorphic systems based on memristors are considered promising approaches to the hardware realization of artificial intelligence systems with efficient information processing. However, a major bottleneck in the physical implementation of these systems is the strong dependence of their performance on the unavoidable variations (cycle‐to‐cycle, c2c, or device‐to‐device, d2d) of memristive devices. Recently, reservoir computing (RC) and spiking neuromorphic systems (SNSs) are separately proposed as valuable options to partially mitigate this problem. Herein, both approaches are combined to create a fully organic system based on 1) volatile polyaniline memristive devices for the reservoir layer and 2) nonvolatile parylene memristors for the SNS readout layer. This combination provides a simpler SNS training procedure compared with the formal neural networks and results in greater robustness to device variability, while ensuring the extraction and encoding of the input critical features (performed by the polyaniline reservoir) and the analysis and classification performed by the SNS layer. Furthermore, the spatiotemporal pattern recognition of the system brings us closer to the implementation of efficient and reliable brain‐inspired computing systems built with partially unreliable analog elements.

Förderung

  • Russian Science Foundation

Zitieren

APA

Matsukatova, A. N., Prudnikov, N. V., Kulagin, V. A., Battistoni, S., Minnekhanov, A. A., Trofimov, A. D., Nesmelov, A. A., Zavyalov, S. A., Malakhova, Y. N., Parmeggiani, M., Ballesio, A., Marasso, S. L., Chvalun, S. N., Demin, V. A., Emelyanov, A. V., & Erokhin, V. (2023). Combination of Organic‐Based Reservoir Computing and Spiking Neuromorphic Systems for a Robust and Efficient Pattern Classification. Advanced Intelligent Systems, 5(6). https://doi.org/10.1002/aisy.202200407

Vancouver

Matsukatova AN, Prudnikov NV, Kulagin VA, Battistoni S, Minnekhanov AA, Trofimov AD, et al. Combination of Organic‐Based Reservoir Computing and Spiking Neuromorphic Systems for a Robust and Efficient Pattern Classification. Advanced Intelligent Systems. 2023;5(6). doi:10.1002/aisy.202200407

BibTeX
@article{Matsukatova2023,
  author = {Matsukatova, Anna N. and Prudnikov, Nikita V. and Kulagin, Vsevolod A. and Battistoni, Silvia and Minnekhanov, Anton A. and Trofimov, Andrey D. and Nesmelov, Aleksandr A. and Zavyalov, Sergey A. and Malakhova, Yulia N. and Parmeggiani, Matteo and Ballesio, Alberto and Marasso, Simone Luigi and Chvalun, Sergey N. and Demin, Vyacheslav A. and Emelyanov, Andrey V. and Erokhin, Victor},
  title = {Combination of Organic‐Based Reservoir Computing and Spiking Neuromorphic Systems for a Robust and Efficient Pattern Classification},
  journal = {Advanced Intelligent Systems},
  year = {2023},
  volume = {5},
  number = {6},
  doi = {10.1002/aisy.202200407}
}
Kostenlos starten →