Analog memristive time dependent learning using discrete nanoscale RRAM devices

Aniket Singha; Bhaskaran Muralidharan; Bipin Rajendran

doi:10.1109/IJCNN.2014.6889915

Analog memristive time dependent learning using discrete nanoscale RRAM devices

Aniket Singha, Bhaskaran Muralidharan, Bipin Rajendran

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

9 Scopus citations

Abstract

We propose a scheme that mimics the analog time dependent learning characteristics of biological synapses using a small set of discrete nanoscale RRAM devices whose switching voltages vary stochastically. Using numerical models and simulations, we demonstrate that a voltage limited analog memristor operating in the tunneling regime and a parallel combination of 10 RRAM devices having discrete resistance states (two resistance states high and low), can both be employed as artificial synapses with similar statistical performance. We also show that by appropriately choosing the programming voltages and hence the switching probability of the RRAM devices, it is possible to tune the relative conductance of the synaptic element anywhere in the range of 2-100. This paper thus shows the possibility of using discrete RRAM devices to realize an analog functionality in artificial learning systems.

Original language	English (US)
Title of host publication	Proceedings of the International Joint Conference on Neural Networks
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	2248-2255
Number of pages	8
ISBN (Electronic)	9781479914845
DOIs	https://doi.org/10.1109/IJCNN.2014.6889915
State	Published - Sep 3 2014
Externally published	Yes
Event	2014 International Joint Conference on Neural Networks, IJCNN 2014 - Beijing, China Duration: Jul 6 2014 → Jul 11 2014

Publication series

Name	Proceedings of the International Joint Conference on Neural Networks

Other

Other	2014 International Joint Conference on Neural Networks, IJCNN 2014
Country/Territory	China
City	Beijing
Period	7/6/14 → 7/11/14

All Science Journal Classification (ASJC) codes

Software
Artificial Intelligence

Keywords

Memristor
Neuromorphic Computing
Spike Timing Dependent Plasticity

Access to Document

10.1109/IJCNN.2014.6889915

Cite this

Singha, A., Muralidharan, B., & Rajendran, B. (2014). Analog memristive time dependent learning using discrete nanoscale RRAM devices. In Proceedings of the International Joint Conference on Neural Networks (pp. 2248-2255). Article 6889915 (Proceedings of the International Joint Conference on Neural Networks). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IJCNN.2014.6889915

@inproceedings{9c82ce5cc0b849b5abc9f20d55b680fd,

title = "Analog memristive time dependent learning using discrete nanoscale RRAM devices",

abstract = "We propose a scheme that mimics the analog time dependent learning characteristics of biological synapses using a small set of discrete nanoscale RRAM devices whose switching voltages vary stochastically. Using numerical models and simulations, we demonstrate that a voltage limited analog memristor operating in the tunneling regime and a parallel combination of 10 RRAM devices having discrete resistance states (two resistance states high and low), can both be employed as artificial synapses with similar statistical performance. We also show that by appropriately choosing the programming voltages and hence the switching probability of the RRAM devices, it is possible to tune the relative conductance of the synaptic element anywhere in the range of 2-100. This paper thus shows the possibility of using discrete RRAM devices to realize an analog functionality in artificial learning systems.",

keywords = "Memristor, Neuromorphic Computing, Spike Timing Dependent Plasticity",

author = "Aniket Singha and Bhaskaran Muralidharan and Bipin Rajendran",

note = "Publisher Copyright: {\textcopyright} 2014 IEEE.; 2014 International Joint Conference on Neural Networks, IJCNN 2014 ; Conference date: 06-07-2014 Through 11-07-2014",

year = "2014",

month = sep,

day = "3",

doi = "10.1109/IJCNN.2014.6889915",

language = "English (US)",

series = "Proceedings of the International Joint Conference on Neural Networks",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "2248--2255",

booktitle = "Proceedings of the International Joint Conference on Neural Networks",

address = "United States",

}

Singha, A, Muralidharan, B & Rajendran, B 2014, Analog memristive time dependent learning using discrete nanoscale RRAM devices. in Proceedings of the International Joint Conference on Neural Networks., 6889915, Proceedings of the International Joint Conference on Neural Networks, Institute of Electrical and Electronics Engineers Inc., pp. 2248-2255, 2014 International Joint Conference on Neural Networks, IJCNN 2014, Beijing, China, 7/6/14. https://doi.org/10.1109/IJCNN.2014.6889915

Analog memristive time dependent learning using discrete nanoscale RRAM devices. / Singha, Aniket; Muralidharan, Bhaskaran; Rajendran, Bipin.
Proceedings of the International Joint Conference on Neural Networks. Institute of Electrical and Electronics Engineers Inc., 2014. p. 2248-2255 6889915 (Proceedings of the International Joint Conference on Neural Networks).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Analog memristive time dependent learning using discrete nanoscale RRAM devices

AU - Singha, Aniket

AU - Muralidharan, Bhaskaran

AU - Rajendran, Bipin

PY - 2014/9/3

Y1 - 2014/9/3

N2 - We propose a scheme that mimics the analog time dependent learning characteristics of biological synapses using a small set of discrete nanoscale RRAM devices whose switching voltages vary stochastically. Using numerical models and simulations, we demonstrate that a voltage limited analog memristor operating in the tunneling regime and a parallel combination of 10 RRAM devices having discrete resistance states (two resistance states high and low), can both be employed as artificial synapses with similar statistical performance. We also show that by appropriately choosing the programming voltages and hence the switching probability of the RRAM devices, it is possible to tune the relative conductance of the synaptic element anywhere in the range of 2-100. This paper thus shows the possibility of using discrete RRAM devices to realize an analog functionality in artificial learning systems.

AB - We propose a scheme that mimics the analog time dependent learning characteristics of biological synapses using a small set of discrete nanoscale RRAM devices whose switching voltages vary stochastically. Using numerical models and simulations, we demonstrate that a voltage limited analog memristor operating in the tunneling regime and a parallel combination of 10 RRAM devices having discrete resistance states (two resistance states high and low), can both be employed as artificial synapses with similar statistical performance. We also show that by appropriately choosing the programming voltages and hence the switching probability of the RRAM devices, it is possible to tune the relative conductance of the synaptic element anywhere in the range of 2-100. This paper thus shows the possibility of using discrete RRAM devices to realize an analog functionality in artificial learning systems.

KW - Memristor

KW - Neuromorphic Computing

KW - Spike Timing Dependent Plasticity

UR - http://www.scopus.com/inward/record.url?scp=84908472304&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84908472304&partnerID=8YFLogxK

U2 - 10.1109/IJCNN.2014.6889915

DO - 10.1109/IJCNN.2014.6889915

M3 - Conference contribution

AN - SCOPUS:84908472304

T3 - Proceedings of the International Joint Conference on Neural Networks

SP - 2248

EP - 2255

BT - Proceedings of the International Joint Conference on Neural Networks

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2014 International Joint Conference on Neural Networks, IJCNN 2014

Y2 - 6 July 2014 through 11 July 2014

ER -

Singha A, Muralidharan B, Rajendran B. Analog memristive time dependent learning using discrete nanoscale RRAM devices. In Proceedings of the International Joint Conference on Neural Networks. Institute of Electrical and Electronics Engineers Inc. 2014. p. 2248-2255. 6889915. (Proceedings of the International Joint Conference on Neural Networks). doi: 10.1109/IJCNN.2014.6889915

Analog memristive time dependent learning using discrete nanoscale RRAM devices

Abstract

Publication series

Other

All Science Journal Classification (ASJC) codes

Keywords

Access to Document

Other files and links

Fingerprint

Cite this