Memristor models for machine learning

DOI10.1162/NECO_A_00694MaRDI QIDQ5380222zbMATH OpenOpenAlexWikidataFDO

Authors Juan P. Carbajal, Joni Dambre, Michiel Hermans, Benjamin Schrauwen

Publication date 4 June 2019

Published in Neural Computation (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1406.2210

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Analytic circuit theory (94C05)

Abstract: In the quest for alternatives to traditional CMOS, it is being suggested that digital computing efficiency and power can be improved by matching the precision to the application. Many applications do not need the high precision that is being used today. In particular, large gains in area- and power efficiency could be achieved by dedicated analog realizations of approximate computing engines. In this work, we explore the use of memristor networks for analog approximate computation, based on a machine learning framework called reservoir computing. Most experimental investigations on the dynamics of memristors focus on their nonvolatile behavior. Hence, the volatility that is present in the developed technologies is usually unwanted and it is not included in simulation models. In contrast, in reservoir computing, volatility is not only desirable but necessary. Therefore, in this work, we propose two different ways to incorporate it into memristor simulation models. The first is an extension of Strukov's model and the second is an equivalent Wiener model approximation. We analyze and compare the dynamical properties of these models and discuss their implications for the memory and the nonlinear processing capacity of memristor networks. Our results indicate that device variability, increasingly causing problems in traditional computer design, is an asset in the context of reservoir computing. We conclude that, although both models could lead to useful memristor based reservoir computing systems, their computational performance will differ. Therefore, experimental modeling research is required for the development of accurate volatile memristor models.

Recommendations

• Memristor computing systems
• Adaptive computing by memristor circuits
• Revisiting Memristor Properties
• A novel modeling methodology for memristive systems using homotopy perturbation methods
• Memristive Chebyshev neural network and its applications in function approximation

Cites work

• Duality of complex systems built from higher-order elements
• Echo state property linked to an input: exploring a fundamental characteristic of recurrent neural networks
• Encyclopaedia of mathematics. Supplement volume III
• Liquid state machines: motivation, theory, and applications
• Memory in linear recurrent neural networks in continuous time
• Output frequency characteristics of nonlinear systems
• Output frequency response function of nonlinear Volterra systems
• PHASE DIAGRAMS AND SCALING REGIMES FOR A CONTINUUM MODEL OF THE GROWTH OF THIN COMPOSITE FILMS
• Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations

Cited in

(5)

• Finite-time projective synchronization of memristor-based delay fractional-order neural networks
• Phase-type distributions for studying variability in resistive memories
• Highly accurate doublet generator for memristor-based analog memory
• Memristive perceptron for combinational logic classification
• Memristor computing systems

Describes a project that uses

Uses Software

• SAGE

This page was built for publication: Memristor models for machine learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5380222)