Autors: Kirilov, S. M., Zaykov, I. D.
Title: A Neural Network with HfO2 Memristors
Keywords: neural network, memristor synapse, hafnium dioxide, memristo

Abstract: In the last twenty years, the neural networks are under intensive analyses. One of the main ideas of the scientists is to partially replace some of their CMOS-based elements by memristors. Memristors are preferred for application due to their memory effect, low power consumption and nano-size dimensions. The purpose of this paper is to propose an analysis of a feed-forward neural network with HfO2 memristor-based synapses for XOR logic function emulation. The considered network uses synaptic devices with a memristor, resistor and a differential amplifier. The proposed synaptic scheme can ensure positive, zero and negative synaptic weights. For the neural network analysis several classical and modified HfO2 memristor models are used. The network is successfully tested in LTSPICE. The occurrence of convergence problems is reduced by replacing the standard step function in the models by its smooth and differentiable analogue. The capability of the modified models for operation in comple



    PROCEEDINGS OF THE TECHNICAL UNIVERSITY OF SOFIA, vol. 71, issue 1, pp. 30-33, 2021, Bulgaria, TU-Sofia,

    Вид: публикация в международен форум, публикация в реферирано издание, индексирана в Google Scholar