Memcapacitive neural networks

Abstract

It is shown that memcapacitive (memory capacitive) systems can be used as synapses in artificial neural networks. As an example of the proposed approach, the architecture of an integrate-and-fire neural network based on memcapacitive synapses is discussed. Moreover, it has been demonstrated that the spike-timing-dependent plasticity can be simply realised with some of these devices. Memcapacitive synapses are a low-energy alternative to memristive synapses for neuromorphic computation. © 2014 The Institution of Engineering and Technology.