Modeling the Dynamics of Spiking Networks with Memristor-Based STDP to Solve Classification Tasks

Alexander Sboev, Danila Vlasov, Roman Rybka, Yury Davydov, Alexey Serenko and Vyacheslav Demin
Additional contact information
Alexander Sboev: National Research Centre “Kurchatov Institute”, 123182 Moscow, Russia
Danila Vlasov: National Research Centre “Kurchatov Institute”, 123182 Moscow, Russia
Roman Rybka: National Research Centre “Kurchatov Institute”, 123182 Moscow, Russia
Yury Davydov: National Research Centre “Kurchatov Institute”, 123182 Moscow, Russia
Alexey Serenko: National Research Centre “Kurchatov Institute”, 123182 Moscow, Russia
Vyacheslav Demin: National Research Centre “Kurchatov Institute”, 123182 Moscow, Russia

Mathematics, 2021, vol. 9, issue 24, 1-10

Abstract: The problem with training spiking neural networks (SNNs) is relevant due to the ultra-low power consumption these networks could exhibit when implemented in neuromorphic hardware. The ongoing progress in the fabrication of memristors, a prospective basis for analogue synapses, gives relevance to studying the possibility of SNN learning on the base of synaptic plasticity models, obtained by fitting the experimental measurements of the memristor conductance change. The dynamics of memristor conductances is (necessarily) nonlinear, because conductance changes depend on the spike timings, which neurons emit in an all-or-none fashion. The ability to solve classification tasks was previously shown for spiking network models based on the bio-inspired local learning mechanism of spike-timing-dependent plasticity (STDP), as well as with the plasticity that models the conductance change of nanocomposite (NC) memristors. Input data were presented to the network encoded into the intensities of Poisson input spike sequences. This work considers another approach for encoding input data into input spike sequences presented to the network: temporal encoding, in which an input vector is transformed into relative timing of individual input spikes. Since temporal encoding uses fewer input spikes, the processing of each input vector by the network can be faster and more energy-efficient. The aim of the current work is to show the applicability of temporal encoding to training spiking networks with three synaptic plasticity models: STDP, NC memristor approximation, and PPX memristor approximation. We assess the accuracy of the proposed approach on several benchmark classification tasks: Fisher’s Iris, Wisconsin breast cancer, and the pole balancing task (CartPole). The accuracies achieved by SNN with memristor plasticity and conventional STDP are comparable and are on par with classic machine learning approaches.

Keywords: spiking neural networks; synaptic plasticity; spike-timing-dependent plasticity; memristor (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2021
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/9/24/3237/pdf (application/pdf)
https://www.mdpi.com/2227-7390/9/24/3237/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:9:y:2021:i:24:p:3237-:d:702266

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().