Vowel recognition with four coupled spin-torque nano-oscillators

Abstract

In recent years, artificial neural networks have become the flagship algorithm of artificial intelligence 1 . 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 2-7 , for computing complex problems with small size networks [7][8][9][10][11] . This approach is especially interesting for hardware implementations, as emerging nanoelectronic devices can provide highly compact and energy-efficient non-linear auto-oscillators that mimic the periodic spiking activity of biological neurons [12][13][14][15][16] . The dynamical couplings between oscillators can then be used to mediate the synaptic communication between neurons. However, one major challenge towards implementing these models with nano-devices is to achieve learning, which requires finely controlling and tuning their coupled oscillations 17 . The dynamical features of nanodevices can indeed be difficult to control, and prone to noise and variability 18 . In this work, we show that the outstanding tunability of spintronic nano-oscillators, i.e. the possibility to widely and accurately control their frequency through electrical current and magnetic field, can solve 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 outstanding 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 non-linear dynamical features: here, oscillations and synchronization. This demonstration of real-time learning with an array of four spin-torque nano-oscillators is a milestone for spintronics-based neuromorphic computing.Spin-torque nano-oscillators are natural candidates for building hardware neural networks made of coupled nanoscale oscillators [8][9][10]13,15,18,19 . These nanoscale magnetic tunnel junctions emit microwave

Bridging Biological and Artificial Neural Networks with Emerging Neuromorphic Devices: Fundamentals, Progress, and Challenges

“…[299,300] Second, brain uses sophisticated mechanisms to maintain the total amount of excitation and inhibition in the circuit to be roughly the same. [301,302] Third, inhibitory neurons act as gates to control aspects of local processing and ensure spatiotemporal coordination, often mediated by different kinds of interneurons, such as output gates (chandelier neurons), input gates (somatostain neurons), and plasticity gates (VIP neurons).…”

Spintronics, from giant magnetoresistance to magnetic skyrmions and topological insulators

“…What will be the next important innovations? The ultra-low power topological logic devices proposed by the researchers at Intel Corporation [84] the STToscillator-based neuromorphic devices designed for deep learning [120] ? [5] (measurements at 4.2 K).…”

2D Layered Materials for Memristive and Neuromorphic Applications

“…Mater. Previous studies have demonstrated attainable vowel recognition [172,173] based on spin transfer torque nano-oscillators, which shows feasibility of combing spintronic devices and neuromorphic computing together. Recent work has demonstrated that phase transition from 2H-MoTe 2 to 2H d structure shows promising application in high-performance memristive devices.…”