Vowel recognition with four coupled spin-torque nano-oscillators

Miguel Romera, Philippe Talatchian, Sumito Tsunegi, Flavio Abreu Araujo, Vincent Cros, Paolo Bortolotti, Juan Trastoy, Kay Yakushiji, Akio Fukushima, Hitoshi Kubota, Shinji Yuasa, Maxence Ernoult, Damir Vodenicarevic, Tifenn Hirtzlin, Nicolas Locatelli, Damien Querlioz () and Julie Grollier ()
Additional contact information
Miguel Romera: Université Paris-Sud, Université Paris-Saclay
Philippe Talatchian: Université Paris-Sud, Université Paris-Saclay
Sumito Tsunegi: Spintronics Research Center
Flavio Abreu Araujo: Université Paris-Sud, Université Paris-Saclay
Vincent Cros: Université Paris-Sud, Université Paris-Saclay
Paolo Bortolotti: Université Paris-Sud, Université Paris-Saclay
Juan Trastoy: Université Paris-Sud, Université Paris-Saclay
Kay Yakushiji: Spintronics Research Center
Akio Fukushima: Spintronics Research Center
Hitoshi Kubota: Spintronics Research Center
Shinji Yuasa: Spintronics Research Center
Maxence Ernoult: Université Paris-Sud, Université Paris-Saclay
Damir Vodenicarevic: Centre de Nanosciences et de Nanotechnologies, CNRS, Université Paris-Sud, Université Paris-Saclay
Tifenn Hirtzlin: Centre de Nanosciences et de Nanotechnologies, CNRS, Université Paris-Sud, Université Paris-Saclay
Nicolas Locatelli: Centre de Nanosciences et de Nanotechnologies, CNRS, Université Paris-Sud, Université Paris-Saclay
Damien Querlioz: Centre de Nanosciences et de Nanotechnologies, CNRS, Université Paris-Sud, Université Paris-Saclay
Julie Grollier: Université Paris-Sud, Université Paris-Saclay

Nature, 2018, vol. 563, issue 7730, 230-234

Abstract: Abstract In recent years, artificial neural networks have become the flagship algorithm of artificial intelligence1. In these systems, neuron activation functions are static, and computing is achieved through standard arithmetic operations. By contrast, a prominent branch of neuroinspired computing embraces the dynamical nature of the brain and proposes to endow each component of a neural network with dynamical functionality, such as oscillations, and to rely on emergent physical phenomena, such as synchronization2–6, for solving complex problems with small networks7–11. This approach is especially interesting for hardware implementations, because emerging nanoelectronic devices can provide compact and energy-efficient nonlinear auto-oscillators that mimic the periodic spiking activity of biological neurons12–16. The dynamical couplings between oscillators can then be used to mediate the synaptic communication between the artificial neurons. One challenge for using nanodevices in this way is to achieve learning, which requires fine control and tuning of their coupled oscillations17; the dynamical features of nanodevices can be difficult to control and prone to noise and variability18. Here we show that the outstanding tunability of spintronic nano-oscillators—that is, the possibility of accurately controlling their frequency across a wide range, through electrical current and magnetic field—can be used to address this challenge. We successfully train a hardware network of four spin-torque nano-oscillators to recognize spoken vowels by tuning their frequencies according to an automatic real-time learning rule. We show that the high experimental recognition rates stem from the ability of these oscillators to synchronize. Our results demonstrate that non-trivial pattern classification tasks can be achieved with small hardware neural networks by endowing them with nonlinear dynamical features such as oscillations and synchronization.

Keywords: Spin Torque Nano-oscillators; Recognition Rate Experiment; Spoken Vowels; Magnetic Tunnel Junctions (MTJ); Vowel Classes (search for similar items in EconPapers)
Date: 2018
References: Add references at CitEc
Citations: View citations in EconPapers (16)

Downloads: (external link)
https://www.nature.com/articles/s41586-018-0632-y Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:nature:v:563:y:2018:i:7730:d:10.1038_s41586-018-0632-y

Ordering information: This journal article can be ordered from
https://www.nature.com/

DOI: 10.1038/s41586-018-0632-y

Access Statistics for this article

Nature is currently edited by Magdalena Skipper

More articles in Nature from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().