Magnetic tunnel junction enabled all-spin stochastic spiking neural network

Gopalakrishnan Srinivasan, Abhronil Sengupta, Kaushik Roy

Research output: Chapter in Book/Report/Conference proceedingConference contribution

15 Citations (Scopus)

Abstract

Biologically-inspired spiking neural networks (SNNs) have attracted significant research interest due to their inherent computational efficiency in performing classification and recognition tasks. The conventional CMOS-based implementations of large-scale SNNs are power intensive. This is a consequence of the fundamental mismatch between the technology used to realize the neurons and synapses, and the neuroscience mechanisms governing their operation, leading to area-expensive circuit designs. In this work, we present a three-terminal spintronic device, namely, the magnetic tunnel junction (MTJ)-heavy metal (HM) heterostructure that is inherently capable of emulating the neuronal and synaptic dynamics. We exploit the stochastic switching behavior of the MTJ in the presence of thermal noise to mimic the probabilistic spiking of cortical neurons, and the conditional change in the state of a binary synapse based on the pre- and post-synaptic spiking activity required for plasticity. We demonstrate the efficacy of a crossbar organization of our MTJ-HM based stochastic SNN in digit recognition using a comprehensive device-circuit-system simulation framework. The energy efficiency of the proposed system stems from the ultra-low switching energy of the MTJ-HM device, and the in-memory computation rendered possible by the localized arrangement of the computational units (neurons) and non-volatile synaptic memory in such crossbar architectures.

Original languageEnglish (US)
Title of host publicationProceedings of the 2017 Design, Automation and Test in Europe, DATE 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages530-535
Number of pages6
ISBN (Electronic)9783981537093
DOIs
StatePublished - May 11 2017
Event20th Design, Automation and Test in Europe, DATE 2017 - Swisstech, Lausanne, Switzerland
Duration: Mar 27 2017Mar 31 2017

Publication series

NameProceedings of the 2017 Design, Automation and Test in Europe, DATE 2017

Other

Other20th Design, Automation and Test in Europe, DATE 2017
CountrySwitzerland
CitySwisstech, Lausanne
Period3/27/173/31/17

Fingerprint

Tunnel junctions
Heavy metals
Neurons
Neural networks
Data storage equipment
Magnetoelectronics
Thermal noise
Networks (circuits)
Computational efficiency
Plasticity
Energy efficiency
Heterojunctions

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Hardware and Architecture
  • Safety, Risk, Reliability and Quality

Cite this

Srinivasan, G., Sengupta, A., & Roy, K. (2017). Magnetic tunnel junction enabled all-spin stochastic spiking neural network. In Proceedings of the 2017 Design, Automation and Test in Europe, DATE 2017 (pp. 530-535). [7927045] (Proceedings of the 2017 Design, Automation and Test in Europe, DATE 2017). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.23919/DATE.2017.7927045
Srinivasan, Gopalakrishnan ; Sengupta, Abhronil ; Roy, Kaushik. / Magnetic tunnel junction enabled all-spin stochastic spiking neural network. Proceedings of the 2017 Design, Automation and Test in Europe, DATE 2017. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 530-535 (Proceedings of the 2017 Design, Automation and Test in Europe, DATE 2017).
@inproceedings{b5f114cca8564e9498249fac43b97883,
title = "Magnetic tunnel junction enabled all-spin stochastic spiking neural network",
abstract = "Biologically-inspired spiking neural networks (SNNs) have attracted significant research interest due to their inherent computational efficiency in performing classification and recognition tasks. The conventional CMOS-based implementations of large-scale SNNs are power intensive. This is a consequence of the fundamental mismatch between the technology used to realize the neurons and synapses, and the neuroscience mechanisms governing their operation, leading to area-expensive circuit designs. In this work, we present a three-terminal spintronic device, namely, the magnetic tunnel junction (MTJ)-heavy metal (HM) heterostructure that is inherently capable of emulating the neuronal and synaptic dynamics. We exploit the stochastic switching behavior of the MTJ in the presence of thermal noise to mimic the probabilistic spiking of cortical neurons, and the conditional change in the state of a binary synapse based on the pre- and post-synaptic spiking activity required for plasticity. We demonstrate the efficacy of a crossbar organization of our MTJ-HM based stochastic SNN in digit recognition using a comprehensive device-circuit-system simulation framework. The energy efficiency of the proposed system stems from the ultra-low switching energy of the MTJ-HM device, and the in-memory computation rendered possible by the localized arrangement of the computational units (neurons) and non-volatile synaptic memory in such crossbar architectures.",
author = "Gopalakrishnan Srinivasan and Abhronil Sengupta and Kaushik Roy",
year = "2017",
month = "5",
day = "11",
doi = "10.23919/DATE.2017.7927045",
language = "English (US)",
series = "Proceedings of the 2017 Design, Automation and Test in Europe, DATE 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "530--535",
booktitle = "Proceedings of the 2017 Design, Automation and Test in Europe, DATE 2017",
address = "United States",

}

Srinivasan, G, Sengupta, A & Roy, K 2017, Magnetic tunnel junction enabled all-spin stochastic spiking neural network. in Proceedings of the 2017 Design, Automation and Test in Europe, DATE 2017., 7927045, Proceedings of the 2017 Design, Automation and Test in Europe, DATE 2017, Institute of Electrical and Electronics Engineers Inc., pp. 530-535, 20th Design, Automation and Test in Europe, DATE 2017, Swisstech, Lausanne, Switzerland, 3/27/17. https://doi.org/10.23919/DATE.2017.7927045

Magnetic tunnel junction enabled all-spin stochastic spiking neural network. / Srinivasan, Gopalakrishnan; Sengupta, Abhronil; Roy, Kaushik.

Proceedings of the 2017 Design, Automation and Test in Europe, DATE 2017. Institute of Electrical and Electronics Engineers Inc., 2017. p. 530-535 7927045 (Proceedings of the 2017 Design, Automation and Test in Europe, DATE 2017).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Magnetic tunnel junction enabled all-spin stochastic spiking neural network

AU - Srinivasan, Gopalakrishnan

AU - Sengupta, Abhronil

AU - Roy, Kaushik

PY - 2017/5/11

Y1 - 2017/5/11

N2 - Biologically-inspired spiking neural networks (SNNs) have attracted significant research interest due to their inherent computational efficiency in performing classification and recognition tasks. The conventional CMOS-based implementations of large-scale SNNs are power intensive. This is a consequence of the fundamental mismatch between the technology used to realize the neurons and synapses, and the neuroscience mechanisms governing their operation, leading to area-expensive circuit designs. In this work, we present a three-terminal spintronic device, namely, the magnetic tunnel junction (MTJ)-heavy metal (HM) heterostructure that is inherently capable of emulating the neuronal and synaptic dynamics. We exploit the stochastic switching behavior of the MTJ in the presence of thermal noise to mimic the probabilistic spiking of cortical neurons, and the conditional change in the state of a binary synapse based on the pre- and post-synaptic spiking activity required for plasticity. We demonstrate the efficacy of a crossbar organization of our MTJ-HM based stochastic SNN in digit recognition using a comprehensive device-circuit-system simulation framework. The energy efficiency of the proposed system stems from the ultra-low switching energy of the MTJ-HM device, and the in-memory computation rendered possible by the localized arrangement of the computational units (neurons) and non-volatile synaptic memory in such crossbar architectures.

AB - Biologically-inspired spiking neural networks (SNNs) have attracted significant research interest due to their inherent computational efficiency in performing classification and recognition tasks. The conventional CMOS-based implementations of large-scale SNNs are power intensive. This is a consequence of the fundamental mismatch between the technology used to realize the neurons and synapses, and the neuroscience mechanisms governing their operation, leading to area-expensive circuit designs. In this work, we present a three-terminal spintronic device, namely, the magnetic tunnel junction (MTJ)-heavy metal (HM) heterostructure that is inherently capable of emulating the neuronal and synaptic dynamics. We exploit the stochastic switching behavior of the MTJ in the presence of thermal noise to mimic the probabilistic spiking of cortical neurons, and the conditional change in the state of a binary synapse based on the pre- and post-synaptic spiking activity required for plasticity. We demonstrate the efficacy of a crossbar organization of our MTJ-HM based stochastic SNN in digit recognition using a comprehensive device-circuit-system simulation framework. The energy efficiency of the proposed system stems from the ultra-low switching energy of the MTJ-HM device, and the in-memory computation rendered possible by the localized arrangement of the computational units (neurons) and non-volatile synaptic memory in such crossbar architectures.

UR - http://www.scopus.com/inward/record.url?scp=85020202697&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85020202697&partnerID=8YFLogxK

U2 - 10.23919/DATE.2017.7927045

DO - 10.23919/DATE.2017.7927045

M3 - Conference contribution

AN - SCOPUS:85020202697

T3 - Proceedings of the 2017 Design, Automation and Test in Europe, DATE 2017

SP - 530

EP - 535

BT - Proceedings of the 2017 Design, Automation and Test in Europe, DATE 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Srinivasan G, Sengupta A, Roy K. Magnetic tunnel junction enabled all-spin stochastic spiking neural network. In Proceedings of the 2017 Design, Automation and Test in Europe, DATE 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 530-535. 7927045. (Proceedings of the 2017 Design, Automation and Test in Europe, DATE 2017). https://doi.org/10.23919/DATE.2017.7927045