Design and simulation of memristor-based neural networks

TL;DR

This paper explores the design and simulation of memristor-based neural networks as energy-efficient alternatives, demonstrating their feasibility through accurate modeling and successful neural network implementations.

Contribution

It introduces a physical model for simulating commercial memristors and demonstrates neural network designs using this model, highlighting their potential for low-power applications.

Findings

Memristor-based neural networks show promising performance.

Simulations confirm the feasibility of memristor circuits for neural computation.

Low power consumption potential demonstrated.

Abstract

In recent times, neural networks have been gaining increasing importance in fields such as pattern recognition and computer vision. However, their usage entails significant energy and hardware costs, limiting the domains in which this technology can be employed. In this context, the feasibility of utilizing analog circuits based on memristors as efficient alternatives in neural network inference is being considered. Memristors stand out for their configurability and low power consumption. To study the feasibility of using these circuits, a physical model has been adapted to accurately simulate the behavior of commercial memristors from KNOWM. Using this model, multiple neural networks have been designed and simulated, yielding highly satisfactory results.