Organic memristive device as key element for neuromorphic networks

Erokhin, Victor

doi:10.1063/1.4912535

Cited by 1 publication

(1 citation statement)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Combined with plasticity, neuro-evolutionary controllers have shown increased performance compared to similarly-evolved nonplastic-synapse networks [26], [31]. Related research on neuromorphic memristive networks includes the use of conductive polymers [9] and crossbar implementations [18].…”

Section: Memristive Spiking Networkmentioning

confidence: 99%

Evolving Unipolar Memristor Spiking Neural Networks

Howard¹,

Bull

Costello

2015

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract-Neuromorphic computing -brainlike computing in hardware -typically requires myriad CMOS spiking neurons interconnected by a dense mesh of nanoscale plastic synapses. Memristors are frequently cited as strong synapse candidates due to their statefulness and potential for low-power implementations. To date, plentiful research has focused on the bipolar memristor synapse, which is capable of incremental weight alterations and can provide adaptive self-organisation under a Hebbian learning scheme. In this paper we consider the Unipolar memristor synapse -a device capable of nonHebbian switching between only two states (conductive and resistive) through application of a suitable input voltage -and discuss its suitability for neuromorphic systems. A self-adaptive evolutionary process is used to autonomously find highly fit network configurations. Experimentation on two robotics tasks shows that unipolar memristor networks evolve task-solving controllers faster than both bipolar memristor networks and networks containing constant nonplastic connections whilst performing at least comparably.

show abstract