RT Journal Article
T1 Vowel recognition with four coupled spin-torque nano-oscillators
A1 Romera Rabasa, Miguel Álvaro
A1 Talatchian, Philippe
A1 Tsunegi, Sumito
A1 Abreu Araujo, Flavio
A1 Cros, Vincent
A1 Bortolotti, Paolo
A1 Trastoy, Juan
A1 Yakushiji, Kay
A1 Fukushima, Akio
A1 Kubota, Hitoshi
A1 Yuasa, Shinji
A1 Ernoult, Maxence
A1 Vodenicarevic, Damir
A1 Hirtzlin, Tifenn
A1 Locatelli, Nicolas
A1 Querlioz, Damien
A1 Grollier, Julie
AB In recent years, artificial neural networks have become the flagship algorithm of artificial intelligence'. 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 synchronization(2-6), for solving complex problems with small networks(7-11). 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 neurons(12-16). 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 oscillations(17); the dynamical features of nanodevices can be difficult to control and prone to noise and variability(18). 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 nanooscillators 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.
PB Nature Research
SN 0028-0836
YR 2018
FD 2018
LK https://hdl.handle.net/20.500.14352/95926
UL https://hdl.handle.net/20.500.14352/95926
LA eng
NO Romera, M., Talatchian, P., Tsunegi, S. et al. Vowel recognition with four coupled spin-torque nano-oscillators. Nature 563, 230–234 (2018). https://doi.org/10.1038/s41586-018-0632-y
NO European Commission
NO Agence Nationale de la Recherche (France)
NO Norwegian Agency for Development Cooperation 
DS Docta Complutense
RD 17 abr 2025