Effect of memristorś potentiation-depression curves peculiarities in the convergence of physical perceptrons

Abstract

Neuromorphic computing aims to emulate the architecture and information processing mechanisms of the mammalian brain. This includes the implementation by hardware of neural networks. Oxide-based memristor arrays with cross-bar architecture appear as a possible physical implementation of neural networks.In this paper, we obtain experimental potentiation-depression (P-D) curves on different manganite-based memristive systems and simulate the learning process of perceptrons for character recognition. We analyze how the specific characteristics of the P-D curves affect the convergence time -- characterized by the EPOCHs-to-convergence (ETC) parameter -- of the network. Our work shows that ETC is reduced for systems displaying P-D curves with relatively low granularity and non-linear and asymmetric response. In addition, we also show that noise injection during the synaptic weight actualization further reduces the ETC. The results obtained here are expected to contribute to the optimization of hardware neural networks based on memristors cross-bar arrays.

arXiv comment10 pages published version

References in corpus (8)

• Training and Operation of an Integrated Neuromorphic Network Based on Metal-Oxide Memristors
• A ferroelectric memristor
• Brain-inspired computing: We need a master plan
• Accurate deep neural network inference using computational phase-change memory
• One-step regression and classification with crosspoint resistive memory arrays
• Large memcapacitance and memristance at Nb:SrTiO${}_3$ / La${}_{0.5}$Sr${}_{0.5}$Mn${}_{0.5}$Co${}_{0.5}$O${}_{3-\delta }$ Topotactic Redox Interface
• Optimization of the multi-mem response of topotactic redox La${}_{1/2}$Sr${}_{1/2}$Mn${}_{1/2}$Co${}_{1/2}$O${}_{3-x}$
• Oxygen vacancies dynamics in redox-based interfaces: Tailoring the memristive response