**Maksim Belyaev \* and Andrei Velichko**

Institute of Physics and Technology, Petrozavodsk State University, 31 Lenina str., Petrozavodsk 185910, Russia; velichko@petrsu.ru

**\*** Correspondence: biomax89@yandex.ru

Received: 27 August 2019; Accepted: 18 September 2019; Published: 20 September 2019

**Abstract:** In this paper, we present an electrical circuit of a leaky integrate-and-fire neuron with one VO<sup>2</sup> switch, which models the properties of biological neurons. Based on VO<sup>2</sup> neurons, a twolayer spiking neural network consisting of nine input and three output neurons is modeled in the SPICE simulator. The network contains excitatory and inhibitory couplings, and implements the winner-takes-all principle in pattern recognition. Using a supervised Spike-Timing-Dependent Plasticity training method and a timing method of information coding, the network was trained to recognize three patterns with dimensions of 3 × 3 pixels. The neural network is able to recognize up to 10<sup>5</sup> images per second, and has the potential to increase the recognition speed further.

**Keywords:** leaky integrate-and-fire neuron; vanadium dioxide; neural network; pattern recognition
