arXiv subjects

Julie Grollier

Publications and source records attributed to Julie Grollier.

At least 19 recordsLinked to original sources

arXiv2026

Fast simulation of nonlinear deep resistive networks for energy-based computation

Deep resistive networks are electronic energy-based systems in which computation is performed by the steady-state voltages of nonlinear circuits. Nonlinear devices enable expressive input-output transformations, but make the circuit equilibria costly to compute during simulation and training. Recent coordinate-descent solvers have achieved large speedups over SPICE-class circuit simulators, but only for nonlinearities modeled as ideal-diode models. This mathematical simplification is not sufficient for practical analog circuits. Here we extend coordinate-descent simulation to realistic monotone nonlinearities, including Shockley diodes, antiparallel diode pairs, and piecewise-linear current-voltage characteristics. With neighboring voltages fixed, each node update remains a scalar Kirchhoff-law solve. Single-exponential characteristics admit closed-form Lambert-(W) updates, while more general monotone characteristics can be handled with scalar root-finding methods. Across networks with one to three hidden layers and hidden widths from 64 to 1024, the solver reproduces matched SPICE steady-state voltages with relative $L_1$ errors below $1.1\times10^{-4}$ for 90% of validation samples, while achieving speedups up to $(1.7\times10^3)$. We further train a $1568\times100\times20$ double-Shockley network on MNIST, reaching about 3.0% test error and reducing the per-epoch training time by roughly $4.4\times10^2$. Together, these results establish a practical route to the circuit-level design and training of large-scale analog energy-based systems incorporating realistic nonlinear devices.

cs.ET↗

arXiv2025

Experimental quantum reservoir computing with a circuit quantum electrodynamics system

Quantum reservoir computing is a machine learning framework that offers ease of training compared to other quantum neural networks, as it does not rely on gradient-based optimization. Learning is performed in a single step on the output features measured from the quantum system. Various implementations of quantum reservoir computing have been explored in simulations, with different measured features. Although simulations have shown that quantum reservoirs present advantages in performance compared to classical reservoirs, experimental implementations have remained scarce. This is due to the challenge of obtaining a large number of output features that are nonlinear transformations of the input data. In this work, we show that even with a circuit quantum electrodynamics system as simple as a single transmon coupled to a readout resonator, we can implement a proof-of-concept realization of quantum reservoir computing. We obtain a large number of nonlinear features from a single physical system by encoding the input data in the amplitude of a coherent drive and measuring the cavity state in the Fock basis. We demonstrate classification of two classical tasks with significantly smaller hardware resources and fewer measured features compared to classical neural networks. Our experimental results are supported by numerical simulations that show additional Kerr nonlinearity is beneficial to reservoir performance. Our work demonstrates a hardware-efficient quantum neural network implementation that can be further scaled up and generalized to other quantum machine learning models.

quant-ph↗

arXiv2025

Training and synchronizing oscillator networks with Equilibrium Propagation

Oscillator networks represent a promising technology for unconventional computing and artificial intelligence. Thus far, these systems have primarily been demonstrated in small-scale implementations, such as Ising Machines for solving combinatorial problems and associative memories for image recognition, typically trained without state-of-the-art gradient-based algorithms. Scaling up oscillator-based systems requires advanced gradient-based training methods that also ensure robustness against frequency dispersion between individual oscillators. Here, we demonstrate through simulations that the Equilibrium Propagation algorithm enables effective gradient-based training of oscillator networks, facilitating synchronization even when initial oscillator frequencies are significantly dispersed. We specifically investigate two oscillator models: purely phase-coupled oscillators and oscillators coupled via both amplitude and phase interactions. Our results show that these oscillator networks can scale successfully to standard image recognition benchmarks, such as achieving nearly 98\% test accuracy on the MNIST dataset, despite noise introduced by imperfect synchronization. This work thus paves the way for practical hardware implementations of large-scale oscillator networks, such as those based on spintronic devices.

cond-mat.dis-nn↗

arXiv2025

Convolutions with Radio-Frequency Spin-Diodes

The classification of radio-frequency (RF) signals is crucial for applications in robotics, traffic control, and medical devices. Spintronic devices, which respond to RF signals via ferromagnetic resonance, offer a promising solution. Recent studies have shown that a neural network of nanoscale magnetic tunnel junctions can classify RF signals without digitization. However, the complexity of these junctions poses challenges for rapid scaling. In this work, we demonstrate that simple spintronic devices, known as metallic spin-diodes, can effectively perform RF classification. These devices consist of NiFe/Pt bilayers and can implement weighted sums of RF inputs. We experimentally show that chains of four spin-diodes can execute 2x2 pixel filters, achieving high-quality convolutions on the Fashion-MNIST dataset. Integrating the hardware spin-diodes in a software network, we achieve a top-1 accuracy of 88 \% on the first 100 images, compared to 88.4 \% for full software with noise, and 90 \% without noise.

eess.SP↗

arXiv2024

Training the parametric interactions in an analog bosonic quantum neural network with Fock basis measurement

Quantum neural networks promise to extend the power of machine learning into the quantum domain, with potential applications ranging from automatic recognition of quantum states to the control of quantum devices. However, their physical implementation and training remain challenging. In particular, the backpropagation algorithm that underpins the efficiency of classical neural networks cannot generally be applied to large quantum systems, as nonlinear quantum dynamics are not efficiently simulable. Instead, variational quantum circuits typically rely on parameter-shift rules or sampling-based gradient estimation. Here we propose a bosonic quantum neural network based on parametrically coupled Gaussian modes. Although the underlying quantum dynamics are linear, nonlinear output features are generated through Fock-basis measurements. Because Gaussian evolution can be efficiently simulated in the Heisenberg representation, the system admits gradient-based optimization by differentiating a classical model of the dynamics, while the forward evolution itself could be implemented on quantum hardware. This hybrid approach enables end-to-end training of physically meaningful parameters without requiring gradient extraction from the experimental device. Such architectures are naturally compatible with circuit quantum electrodynamics platforms featuring tunable parametric couplers, as well as integrated photonic systems with engineered $\chi$(2) or $\chi$(3) nonlinearities. Our results demonstrate that linear bosonic networks combined with nonlinear measurement provide a scalable and trainable route toward experimentally realizable quantum neural networks.

quant-ph↗

arXiv2024

Self-Contrastive Forward-Forward Algorithm

Agents that operate autonomously benefit from lifelong learning capabilities. However, compatible training algorithms must comply with the decentralized nature of these systems, which imposes constraints on both the parameter counts and the computational resources. The Forward-Forward (FF) algorithm is one of these. FF relies only on feedforward operations, the same used for inference, for optimizing layer-wise objectives. This purely forward approach eliminates the need for transpose operations required in traditional backpropagation. Despite its potential, FF has failed to reach state-of-the-art performance on most standard benchmark tasks, in part due to unreliable negative data generation methods for unsupervised learning. In this work, we propose the Self-Contrastive Forward-Forward (SCFF) algorithm, a competitive training method aimed at closing this performance gap. Inspired by standard self-supervised contrastive learning for vision tasks, SCFF generates positive and negative inputs applicable across various datasets. The method demonstrates superior performance compared to existing unsupervised local learning algorithms on several benchmark datasets, including MNIST, CIFAR-10, STL-10, and Tiny ImageNet. We extend FF's application to training recurrent neural networks, expanding its utility to sequential data tasks. These findings pave the way for high-accuracy, real-time learning on resource-constrained edge devices.

cs.LG↗

arXiv2024

Training a multilayer dynamical spintronic network with standard machine learning tools to perform time series classification

The ability to process time-series at low energy cost is critical for many applications. Recurrent neural network, which can perform such tasks, are computationally expensive when implementing in software on conventional computers. Here we propose to implement a recurrent neural network in hardware using spintronic oscillators as dynamical neurons. Using numerical simulations, we build a multi-layer network and demonstrate that we can use backpropagation through time (BPTT) and standard machine learning tools to train this network. Leveraging the transient dynamics of the spintronic oscillators, we solve the sequential digits classification task with $89.83\pm2.91~\%$ accuracy, as good as the equivalent software network. We devise guidelines on how to choose the time constant of the oscillators as well as hyper-parameters of the network to adapt to different input time scales.

cond-mat.dis-nn↗

arXiv2024

Real Space Imaging of Field-Driven Decision-Making in Nanomagnetic Galton Boards

A possible spintronic route to hardware implementation for decision making involves injecting a domain wall into a bifurcated magnetic nanostrip resembling a Y-shaped junction. A decision is made when the domain wall chooses a particular path through the bifurcation. Recently, it was shown that a structure like a nanomagnetic Galton Board, which is essentially an array of interconnected Y-shaped junctions, produces outcomes that are stochastic and therefore relevant to artificial neural networks. However, the exact mechanism leading to the robust nature of randomness is unknown. Here, we directly image the decision-making process in nanomagnetic Galton Boards using Lorentz transmission electron microscopy. We identify that the stochasticity in nanomagnetic Galton Boards arises as a culmination of: (1) topology of the injected domain wall, (2) local disorder, and (3) strength of the applied field. Our results pave the way to a detailed understanding of stochasticity in nanomagnetic networks.

physics.app-ph↗

arXiv2024

Training of Physical Neural Networks

Physical neural networks (PNNs) are a class of neural-like networks that leverage the properties of physical systems to perform computation. While PNNs are so far a niche research area with small-scale laboratory demonstrations, they are arguably one of the most underappreciated important opportunities in modern AI. Could we train AI models 1000x larger than current ones? Could we do this and also have them perform inference locally and privately on edge devices, such as smartphones or sensors? Research over the past few years has shown that the answer to all these questions is likely "yes, with enough research": PNNs could one day radically change what is possible and practical for AI systems. To do this will however require rethinking both how AI models work, and how they are trained - primarily by considering the problems through the constraints of the underlying hardware physics. To train PNNs at large scale, many methods including backpropagation-based and backpropagation-free approaches are now being explored. These methods have various trade-offs, and so far no method has been shown to scale to the same scale and performance as the backpropagation algorithm widely used in deep learning today. However, this is rapidly changing, and a diverse ecosystem of training techniques provides clues for how PNNs may one day be utilized to create both more efficient realizations of current-scale AI models, and to enable unprecedented-scale models.

physics.app-ph↗

arXiv2024

Unsupervised End-to-End Training with a Self-Defined Target

Designing algorithms for versatile AI hardware that can learn on the edge using both labeled and unlabeled data is challenging. Deep end-to-end training methods incorporating phases of self-supervised and supervised learning are accurate and adaptable to input data but self-supervised learning requires even more computational and memory resources than supervised learning, too high for current embedded hardware. Conversely, unsupervised layer-by-layer training, such as Hebbian learning, is more compatible with existing hardware but does not integrate well with supervised learning. To address this, we propose a method enabling networks or hardware designed for end-to-end supervised learning to also perform high-performance unsupervised learning by adding two simple elements to the output layer: Winner-Take-All (WTA) selectivity and homeostasis regularization. These mechanisms introduce a "self-defined target" for unlabeled data, allowing purely unsupervised training for both fully-connected and convolutional layers using backpropagation or equilibrium propagation on datasets like MNIST (up to 99.2%), Fashion-MNIST (up to 90.3%), and SVHN (up to 81.5%). We extend this method to semi-supervised learning, adjusting targets based on data type, achieving 96.6% accuracy with only 600 labeled MNIST samples in a multi-layer perceptron. Our results show that this approach can effectively enable networks and hardware initially dedicated to supervised learning to also perform unsupervised learning, adapting to varying availability of labeled data.

cs.NE↗

arXiv2024

Roadmap for Unconventional Computing with Nanotechnology

In the "Beyond Moore's Law" era, with increasing edge intelligence, domain-specific computing embracing unconventional approaches will become increasingly prevalent. At the same time, adopting a variety of nanotechnologies will offer benefits in energy cost, computational speed, reduced footprint, cyber resilience, and processing power. The time is ripe for a roadmap for unconventional computing with nanotechnologies to guide future research, and this collection aims to fill that need. The authors provide a comprehensive roadmap for neuromorphic computing using electron spins, memristive devices, two-dimensional nanomaterials, nanomagnets, and various dynamical systems. They also address other paradigms such as Ising machines, Bayesian inference engines, probabilistic computing with p-bits, processing in memory, quantum memories and algorithms, computing with skyrmions and spin waves, and brain-inspired computing for incremental learning and problem-solving in severely resource-constrained environments. These approaches have advantages over traditional Boolean computing based on von Neumann architecture. As the computational requirements for artificial intelligence grow 50 times faster than Moore's Law for electronics, more unconventional approaches to computing and signal processing will appear on the horizon, and this roadmap will help identify future needs and challenges. In a very fertile field, experts in the field aim to present some of the dominant and most promising technologies for unconventional computing that will be around for some time to come. Within a holistic approach, the goal is to provide pathways for solidifying the field and guiding future impactful discoveries.

cs.ET↗

arXiv2023

Neuromorphic weighted sums with magnetic skyrmions

Integrating magnetic skyrmions into neuromorphic computing could help improve hardware efficiency and computational power. However, developing a scalable implementation of the weighted sum of neuron signals - a core operation in neural networks - has remained a challenge. Here, we show that weighted sum operations can be performed in a compact, biologically-inspired manner by using the non-volatile and particle-like characteristics of magnetic skyrmions that make them easily countable and summable. The skyrmions are electrically generated in numbers proportional to an input with an efficiency given by a non-volatile weight. The chiral particles are then directed using localized current injections to a location where their presence is quantified through non-perturbative electrical measurements. Our experimental demonstration, which currently has two inputs, can be scaled to accommodate multiple inputs and outputs using a crossbar array design, potentially nearing the energy efficiency observed in biological systems.

cs.ET↗

arXiv2023

Control of the magnetic anisotropy in multi-repeat Pt/Co/Al heterostructures using magneto-ionic gating

Controlling magnetic properties through the application of an electric field is a significant challenge in modern nanomagnetism. In this study, we investigate the magneto-ionic control of magnetic anisotropy in the topmost Co layer in Ta/Pt/[Co/Al/Pt]$_n$/Co/Al/AlO$_\text{x}$ multilayer stacks comprising $n +1$ Co layers and its impact on the magnetic properties of the multilayers. We demonstrate that the perpendicular magnetic anisotropy can be reversibly quenched through gate-driven oxidation of the intermediary Al layer between Co and AlO$_\text{x}$, enabling dynamic control of the magnetic layers contributing to the out-of-plane remanence - varying between $n$ and $n +1$. For multilayer configurations with $n = 2$ and $n = 4$, we observe reversible and non-volatile additions of 1/3 and 1/5, respectively, to the anomalous Hall effect amplitude based on the applied gate voltage. Magnetic imaging reveals that the gate-induced spin-reorientation transition occurs through the propagation of a single 90$^{\circ}$ magnetic domain wall separating the perpendicular and in-plane anisotropy states. In the 5-repetition multilayer, the modification leads to a doubling of the period of the magnetic domains at remanence. These results demonstrate that the magneto-ionic control of the anisotropy of a single magnetic layer can be used to control the magnetic properties of coupled multilayer systems, extending beyond the gating effects on a single magnetic layer.

cond-mat.mtrl-sci↗

arXiv2023

Spiking Dynamics in Dual Free Layer Perpendicular Magnetic Tunnel Junctions

Spintronic devices have recently attracted a lot of attention in the field of unconventional computing due to their non-volatility for short and long term memory, non-linear fast response and relatively small footprint. Here we report how voltage driven magnetization dynamics of dual free layer perpendicular magnetic tunnel junctions enable to emulate spiking neurons in hardware. The output spiking rate was controlled by varying the dc bias voltage across the device. The field-free operation of this two terminal device and its robustness against an externally applied magnetic field make it a suitable candidate to mimic neuron response in a dense Neural Network (NN). The small energy consumption of the device (4-16 pJ/spike) and its scalability are important benefits for embedded applications. This compact perpendicular magnetic tunnel junction structure could finally bring spiking neural networks (SNN) to sub-100nm size elements.

physics.app-ph↗

arXiv2023

Training an Ising Machine with Equilibrium Propagation

Ising machines, which are hardware implementations of the Ising model of coupled spins, have been influential in the development of unsupervised learning algorithms at the origins of Artificial Intelligence (AI). However, their application to AI has been limited due to the complexities in matching supervised training methods with Ising machine physics, even though these methods are essential for achieving high accuracy. In this study, we demonstrate a novel approach to train Ising machines in a supervised way through the Equilibrium Propagation algorithm, achieving comparable results to software-based implementations. We employ the quantum annealing procedure of the D-Wave Ising machine to train a fully-connected neural network on the MNIST dataset. Furthermore, we demonstrate that the machine's connectivity supports convolution operations, enabling the training of a compact convolutional network with minimal spins per neuron. Our findings establish Ising machines as a promising trainable hardware platform for AI, with the potential to enhance machine learning applications.

cs.NE↗

arXiv2023

Quantum reservoir neural network implementation on coherently coupled quantum oscillators

Quantum reservoir computing is a promising approach for quantum neural networks, capable of solving hard learning tasks on both classical and quantum input data. However, current approaches with qubits suffer from limited connectivity. We propose an implementation for quantum reservoir that obtains a large number of densely connected neurons by using parametrically coupled quantum oscillators instead of physically coupled qubits. We analyse a specific hardware implementation based on superconducting circuits: with just two coupled quantum oscillators, we create a quantum reservoir comprising up to 81 neurons. We obtain state-of-the-art accuracy of 99 % on benchmark tasks that otherwise require at least 24 classical oscillators to be solved. Our results give the coupling and dissipation requirements in the system and show how they affect the performance of the quantum reservoir. Beyond quantum reservoir computing, the use of parametrically coupled bosonic modes holds promise for realizing large quantum neural network architectures, with billions of neurons implemented with only 10 coupled quantum oscillators.

quant-ph↗

arXiv2023

Classification of multi-frequency RF signals by extreme learning, using magnetic tunnel junctions as neurons and synapses

Extracting information from radiofrequency (RF) signals using artificial neural networks at low energy cost is a critical need for a wide range of applications from radars to health. These RF inputs are composed of multiples frequencies. Here we show that magnetic tunnel junctions can process analogue RF inputs with multiple frequencies in parallel and perform synaptic operations. Using a backpropagation-free method called extreme learning, we classify noisy images encoded by RF signals, using experimental data from magnetic tunnel junctions functioning as both synapses and neurons. We achieve the same accuracy as an equivalent software neural network. These results are a key step for embedded radiofrequency artificial intelligence.

cond-mat.mes-hall↗

arXiv2023

Compensation of anisotropy in spin-Hall devices for neuromorphic applications

Spintronic nano-oscillators with reduced non-linearity could offer key benefits for realizing neuromorphic applications such as spike-based neurons and frequency multiplexing in neural networks. Here, we experimentally demonstrate the reduction in non-linearity of a spin-Hall nano-oscillator (SHNO) by compensation of its effective magnetic anisotropy. The study involves optimization of Co/Ni multilayer growth to achieve the compensation, followed by spin diode measurements on patterned microstrips to quantify their anisotropy. The relation between the second ($H_{k2}$ = 0.47 mT) and the first order ($H_{k1}^{eff}$ = $-$0.8 mT) anisotropy fields reveals the existence of an easy cone, thereby validating the presence of compensation. Furthermore, we demonstrate a synapse based on the compensated spin diode which has a fixed frequency when the input power is varied. We then study the current-induced auto-oscillation properties of SHNOs on compensated films by patterning nano-constrictions of widths 200 and 100 nm. The invariance of the resonance frequency and linewidth of the compensated SHNO with applied dc current indicates the absence of non-linearity. This independence is maintained irrespective of the applied external fields and its orientations. The compensated SHNO obtained has a linewidth of 1.1 MHz and a peak output power of up to 1 pW/MHz emulating a nano-neuron with a low linewidth and a fixed frequency.

cond-mat.mtrl-sci↗