Memcapacitive neural networks

TL;DR

This paper explores the use of memcapacitive systems as synapses in neural networks, demonstrating their potential for low-energy neuromorphic computing and implementing spike-timing-dependent plasticity.

Contribution

It introduces memcapacitive synapses for neural networks and shows their capability to realize spike-timing-dependent plasticity, offering an energy-efficient alternative to memristive synapses.

Findings

Memcapacitive synapses can be integrated into neural network architectures.

Spike-timing-dependent plasticity can be realized with memcapacitive devices.

Memcapacitive systems offer a low-energy alternative for neuromorphic computation.

Abstract

We show that memcapacitive (memory capacitive) systems can be used as synapses in artificial neural networks. As an example of our approach, we discuss the architecture of an integrate-and-fire neural network based on memcapacitive synapses. Moreover, we demonstrate that the spike-timing-dependent plasticity can be simply realized with some of these devices. Memcapacitive synapses are a low-energy alternative to memristive synapses for neuromorphic computation.