Memristors for the Curious Outsiders

Caravelli, Francesco; Carbajal, Juan Pablo

doi:10.3390/technologies6040118

Cited by 60 publications

(55 citation statements)

References 196 publications

(270 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Because wire resistance in the crossbar cannot be omitted, the proposed scheme makes the memristor crossbar-based perceptron neural network become more possible. The proposed circuit can be applied to memristor-based crossbar architectures which are used in resistive memory and artificial neural networks [34,35,36].…”

Section: Discussionmentioning

confidence: 99%

Compensating Circuit to Reduce the Impact of Wire Resistance in a Memristor Crossbar-Based Perceptron Neural Network

Truong

2019

Micromachines

View full text Add to dashboard Cite

Wire resistance in metal wire is one of the factors that degrade the performance of memristor crossbar circuits. In this paper, an analysis of the impact of wire resistance in a memristor crossbar is performed and a compensating circuit is proposed to reduce the impact of wire resistance in a memristor crossbar-based perceptron neural network. The goal of the analysis is to figure out how wire resistance influences the output voltage of a memristor crossbar. It emerges that the wire resistance on horizontal lines causes the neuron’s output voltage to vary more than the wire resistance on vertical lines. More interesting, the voltage variation caused by wire resistance on horizontal lines increases proportionally to the length of metal wire. The first column has small voltage variation whereas the last column has large voltage variation. In addition, two adjacent columns have almost the same amount of voltage variation. Under these observations, a memristor crossbar-based perceptron neural network with compensating circuit is proposed. The neuron’s outputs of two columns are put into a subtractor circuit to eliminate the voltage variation caused by the wire resistance. The proposed memristor crossbar-based perceptron neural network is trained to recognize the 26 characters. The proposed memristor crossbar shows better recognition rate compared to the previous work when wire resistance is taken into account. The proposed memristor crossbar circuit can maintain the recognition rate as high as 100% when wire resistance is as high as 2.5 Ω. By contrast, the recognition rate of the memristor crossbar without the compensating circuit decreases by 1%, 5%, and 19% when wire resistance is set to be 1.5, 2.0, and 2.5 Ω, respectively.

show abstract

Section: Discussionmentioning

confidence: 99%

Compensating Circuit to Reduce the Impact of Wire Resistance in a Memristor Crossbar-Based Perceptron Neural Network

Truong

2019

Micromachines

View full text Add to dashboard Cite

show abstract

“…Related to applications concerning the measurement of magnetic fields, memristors and memcapacitors for use in neural networks are an emerging technology which demands the ability to weight individual node inputs by means of externally controllable resistance, capacitance, or inductance . Boron‐organo‐silicon fulfills the first two criteria.…”

Section: Applicationsmentioning

confidence: 99%

Electrical Properties of Magnetoactive Boron‐Organo‐Silicon Oxide Polymers

Monkman

Striegl

Prem

et al. 2020

Macro Chemistry & Physics

View full text Add to dashboard Cite

The electrical properties of rheopectic magnetoactive composites comprising boron‐organo‐silicon oxide dielectric matrices containing carbonyl iron microparticles are presented for the first time. The increase in interfacial magnetocapacitance is seen to greatly exceed that experienced when using conventional elastomeric matrices such as polydimethylsiloxane. In addition to the increase in capacitance, a simultaneous and sharp decrease in the parallel electrical resistance over several orders of magnitude is also observed. The effects are time dependent but repeatable. Potential applications include magnetically controlled frequency dependent devices, magnetic sensor systems, weighting elements for neural networks, etc.

show abstract

“…stimulus response confines the memristance between the boundary values R1 and R2, and  is the Heaviside step function. The model leads to a system of the 3 rd order [25]  …”

Section: Model Of Amoeba Adaptationmentioning

confidence: 99%

Emulation of Bio-Inspired Networks

Kolka¹,

Biolková²,

Biolek³

et al. 2019

Adv. sci. technol. eng. syst. j.

View full text Add to dashboard Cite

The paper deals with hardware emulation of bio-inspired devices and nonlinear dynamic processes of complex nature by means of mixed-mode analog-digital emulators. The discretized state model of the emulated system serves for real-time calculation of dependent quantities. In contrast to input-output emulation known in control systems, the proposed approach emulates the ports of an electrical multiport network. The paper discusses the stability of the emulation process and the possibility of partitioning the system into two parts, one being emulated digitally and the other via an analog circuitry. The procedure is illustrated on the example of emulating the Fitzhugh-Nagumo model of neuron and the model of amoeba adaptation. The paper is an extension of our paper presented at the NGCAS 2018 conference in Valletta, Malta. The extended version deals newly with the choice of the integration method and provides a deeper stability analysis and more examples of emulation of biological models.

show abstract

Memristors for the Curious Outsiders

Cited by 60 publications

References 196 publications

Compensating Circuit to Reduce the Impact of Wire Resistance in a Memristor Crossbar-Based Perceptron Neural Network

Compensating Circuit to Reduce the Impact of Wire Resistance in a Memristor Crossbar-Based Perceptron Neural Network

Electrical Properties of Magnetoactive Boron‐Organo‐Silicon Oxide Polymers

Emulation of Bio-Inspired Networks

Contact Info

Product

Resources

About