# Vowel recognition with four coupled spin-torque nano-oscillators

arXiv: https://arxiv.org/abs/1711.02704 · HTML: https://mlsanity.com/paper/1711.02704/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Nov 2017.

## Built on by (most cited first, 22 of 22)

- [Deep physical neural networks enabled by a backpropagation algorithm for arbitrary physical systems](https://mlsanity.com/paper/2104.13386/) (2021)
- [Training of Physical Neural Networks](https://mlsanity.com/paper/2406.03372/) (2024)
- [Backpropagation-free Training of Deep Physical Neural Networks](https://mlsanity.com/paper/2304.11042/) (2023)
- [Applications and Techniques for Fast Machine Learning in Science](https://mlsanity.com/paper/2110.13041/) (2021)
- [Neural Oscillators are Universal](https://mlsanity.com/paper/2305.08753/) (2023)
- [Forecasting the outcome of spintronic experiments with Neural Ordinary Differential Equations](https://mlsanity.com/paper/2108.02318/) (2021)
- [A perspective on physical reservoir computing with nanomagnetic devices](https://mlsanity.com/paper/2212.04851/) (2022)
- [Quantum-limited stochastic optical neural networks operating at a few quanta per activation](https://mlsanity.com/paper/2307.15712/) (2023)
- [Nonlinear Optical Data Transformer for Machine Learning](https://mlsanity.com/paper/2208.09398/) (2022)
- [Spatial Analysis of Physical Reservoir Computers](https://mlsanity.com/paper/2108.01512/) (2021)
- [Virtual reservoir acceleration for CPU and GPU: Case study for coupled spin-torque oscillator reservoir](https://mlsanity.com/paper/2312.01121/) (2023)
- [Voltage-Controlled Magnetoelectric Devices for Neuromorphic Diffusion Process](https://mlsanity.com/paper/2407.12261/) (2024)
- [Scaling Equilibrium Propagation to Deep ConvNets by Drastically Reducing its Gradient Estimator Bias](https://mlsanity.com/paper/2101.05536/) (2021)
- [Reservoir Computing with Magnetic Thin Films](https://mlsanity.com/paper/2101.12700/) (2021)
- [Physical Deep Learning with Biologically Plausible Training Method](https://mlsanity.com/paper/2204.13991/) (2022)
- [Neuromorphic spintronics simulated using an unconventional data-driven Thiele equation approach](https://mlsanity.com/paper/2307.09262/) (2023)
- [Entropy-statistical approach to phase-locking detection of pulse oscillations: application for the analysis of biosignal synchronization](https://mlsanity.com/paper/2406.12906/) (2024)
- [Training a multilayer dynamical spintronic network with standard machine learning tools to perform time series classification](https://mlsanity.com/paper/2408.02835/) (2024)
- [Mechanical in-sensor computing: a programmable meta-sensor for structural damage classification without external electronic power](https://mlsanity.com/paper/2505.18579/) (2025)
- [Reinforcement learning for spin torque oscillator tasks](https://mlsanity.com/paper/2509.10057/) (2025)
- [Laser interferometry as a robust neuromorphic platform for machine learning](https://mlsanity.com/paper/2601.18047/) (2026)
- [Scalable neuromorphic computing from autonomous spiking dynamics in a clockless reconfigurable chip](https://mlsanity.com/paper/2605.16114/) (2026)

## Abstract (arXiv)

Substantial evidence indicates that the brain uses principles of non-linear dynamics in neural processes, providing inspiration for computing with nanoelectronic devices. However, training neural networks composed of dynamical nanodevices requires finely controlling and tuning their coupled oscillations. In this work, we show that the outstanding tunability of spintronic nano-oscillators 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 high frequency tunability of the oscillators and their mutual coupling. 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 is a milestone for spintronics-based neuromorphic computing.