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.
Combination of Organic-Based Reservoir Computing and Spiking Neuromorphic Systems for a Robust and Efficient Pattern Classification / Matsukatova, An; Prudnikov, Nv; Kulagin, Va; Battistoni, S; Minnekhanov, Ad; Trofimov, Aa; Nesmelov, Aa; Zavyalov, Sa; Malakhova, Yn; Parmeggiani, M; Ballesio, A; Marasso, Sl; Chvalun, Sn; Demin, Va; Emelyanov, Av; Erokhin, V. - In: ADVANCED INTELLIGENT SYSTEMS. - ISSN 2640-4567. - 5:6(2023). [10.1002/aisy.202200407]
Combination of Organic-Based Reservoir Computing and Spiking Neuromorphic Systems for a Robust and Efficient Pattern Classification
Parmeggiani, M;Ballesio, A;Marasso, SL;
2023
Abstract
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.File | Dimensione | Formato | |
---|---|---|---|
Advanced Intelligent Systems - 2023 - Matsukatova - Combination of Organic‐Based Reservoir Computing and Spiking.pdf
accesso aperto
Tipologia:
2a Post-print versione editoriale / Version of Record
Licenza:
Creative commons
Dimensione
2.81 MB
Formato
Adobe PDF
|
2.81 MB | Adobe PDF | Visualizza/Apri |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/11583/2983865