Header

UZH-Logo

Maintenance Infos

Guest Editorial: Special Issue on Large-Scale Memristive Systems and Neurochips for Computational Intelligence


James, A Pappachen; Salama, K Nabil; Li, H; Biolek, D; Indiveri, G; Chua, L O (2018). Guest Editorial: Special Issue on Large-Scale Memristive Systems and Neurochips for Computational Intelligence. IEEE Transactions on Emerging Topics in Computational Intelligence, 2(5):320-323.

Abstract

The papers in this special section explore the use of large scale memristive systems and neurochips for computational intelligence. The interest in the application of memristor device as a memory element, neuromorphic device, as a sensor and as a switch for programmable logic circuits has been growing in the last decade. The small size, ease of programmability, low leakage currents, ability to maintain resistance states and CMOS compatibility make the memristor a useful device. The possibility of using memristors to mimic neural circuits and architectures as well as to implement learning for in-memory computing tasks makes it further a versatile device. However, in this early stages of development and exploration, modeling and simulation of the realistic memristors in application to simulating large-scale arrays remains a challenging issue among others. The development of memristive device models that reflect the realistic characteristic of memristor devices is an ongoing challenge. While most memristor models close to reflect the electrical characteristics of the memristors, the time dynamics properties under non-ideal conditions, accurately modeling variability of fabricated memristors, and faster convergence for large circuit simulations are open problems. The electromagnetic issues, thermal issues, and signal integrity challenges are yet to be adequately modeled for these devices.

Abstract

The papers in this special section explore the use of large scale memristive systems and neurochips for computational intelligence. The interest in the application of memristor device as a memory element, neuromorphic device, as a sensor and as a switch for programmable logic circuits has been growing in the last decade. The small size, ease of programmability, low leakage currents, ability to maintain resistance states and CMOS compatibility make the memristor a useful device. The possibility of using memristors to mimic neural circuits and architectures as well as to implement learning for in-memory computing tasks makes it further a versatile device. However, in this early stages of development and exploration, modeling and simulation of the realistic memristors in application to simulating large-scale arrays remains a challenging issue among others. The development of memristive device models that reflect the realistic characteristic of memristor devices is an ongoing challenge. While most memristor models close to reflect the electrical characteristics of the memristors, the time dynamics properties under non-ideal conditions, accurately modeling variability of fabricated memristors, and faster convergence for large circuit simulations are open problems. The electromagnetic issues, thermal issues, and signal integrity challenges are yet to be adequately modeled for these devices.

Statistics

Citations

Dimensions.ai Metrics

Altmetrics

Downloads

0 downloads since deposited on 12 Mar 2019
0 downloads since 12 months

Additional indexing

Item Type:Journal Article, not_refereed, further contribution
Communities & Collections:07 Faculty of Science > Institute of Neuroinformatics
Dewey Decimal Classification:570 Life sciences; biology
Language:English
Date:2018
Deposited On:12 Mar 2019 12:00
Last Modified:25 Sep 2019 00:27
Publisher:Institute of Electrical and Electronics Engineers
Number of Pages:4
ISSN:2471-285X
OA Status:Closed
Publisher DOI:https://doi.org/10.1109/TETCI.2018.2867375

Download

Closed Access: Download allowed only for UZH members