Filament formation in lithium niobate memristors supports neuromorphic programming capability

Memristor crossbars are capable of implementing learning algorithms in a much more energy and area efficient manner compared to traditional systems. However, the programmable nature of memristor crossbars must first be explored on a smaller scale to see which memristor device structures are most suitable for applications in reconfigurable computing. In this paper, we demonstrate the programmability of memristor devices with filamentary switching based on LiNbO₃, a new resistive switching oxide. We show that a range of resistance values can be set within these memristor devices using a pulse train for programming. We also show that a neuromorphic crossbar containing eight memristors was capable of correctly implementing an OR function. This work demonstrates that lithium niobate memristors are strong candidates for use in neuromorphic computing.

     

Flexible memristor based neuromorphic system for implementing multi-layer neural network algorithms

Abstract

This paper describes a memristor-based neuromorphic system that can be used for ex situ training of various multi-layer neural network algorithms. This system is based on an analogue neuron circuit that is capable of performing an accurate dot product calculation. The presented ex situ programming technique can be used to map many key neural algorithms directly onto the grid of resistances in a memristor crossbar. Using this weight-to-crossbar mapping approach along with the memristor based circuit architecture, complex neural algorithms can be easily implemented using this system. Some existing memristor based circuits provide an approximated dot product based on conductance summation, but neuron outputs are not directly correlated to the numerical values obtained in a traditional software approach. To show the effectiveness and versatility of this circuit, two different powerful neural networks were simulated. These include a Restricted Boltzmann Machine for character recognition and a Multilayer Perceptron trained to perform Sobel edge detection. Following these simulations, an analysis was presented that shows how both memristor accuracy and neuron circuit gain relates to output error.     

A fast training method for memristor crossbar based multi-layer neural networks

The capacitance variation of capacitive accelerometer as a function of vibratory movement relative frequency is presented using a developed model validated by simulation and experimental tests. The damping rate effect on accelerometer capacitance variation is studied for four damping rate values. The first value is that of accelerometer used in the experimental tests, the second and third are taken from the recent works and the fourth is the value proposed in this work. A comparative study has been made to mount our improvements on the capacitive accelerometer performances by the comparison between the proposed accelerometers in the recent works. Finally, a new capacitive accelerometer with improved parameters is proposed having many benefits over the existing accelerometers. These benefits are: appropriate choice of damping rate (equal to 0.68), very low measurement error (limited to 0.5%), high accuracy (equal to 99.5%), low consumption of electrical energy and high sensitivity and reliability.