arXiv subjects

Anatole Moureaux

Publications and source records attributed to Anatole Moureaux.

6 recordsLinked to original sources

arXiv2026

Multibit neural inference in a N-ary crossbar architecture

In-memory computing (IMC) is a paradigm that enables neural network inference by computing analog matrix-vector multiplications (MVM) directly in memory crossbar arrays, with the potential for energy efficiency gains over conventional von Neumann architectures. In this work we present a simulation framework for N-ary crossbar architectures that retrieves MVM results with minimal implementation assumptions. The XOR and MNIST classification tasks were successfully inferred using a simulated crossbar array of (4x4) 4-states magnetic tunnel junctions (MTJ). MNIST accuracy reached 93.56% (vs. 97.56% software baseline). PCA dimensionality reduction was shown to drastically lower the number of required operations and improve the software baseline, for only a modest reduction in crossbar inference accuracy. We identified weight quantization as the primary error source, and studied its impact alongside systematic non-idealities and random noise. We find that cell-specific random noise is less detrimental than systematic errors due to averaging across the array. Finally, we demonstrate an optimal number of states per cell that balances quantization error against resistance state resolution to minimize total MVM error.

cs.AR↗

arXiv2026

Spintronics for image recognition: performance benchmarking via data-driven simulations

We present a demonstration of image classification using an extreme learning machine (ELM) based on a unique simulated magnetic tunnel junction (MTJ) delayed in time. As the ground state of the MTJ is a magnetic vortex, we refer to it as a vortex-based spin-torque oscillator (STVO). The dynamics of the magnetic vortex is simulated with a model called the data-driven Thiele equation approach (DD-TEA). This allows to avoid the constraints associated with repeated experimental manipulation for hyperparameters search and benchmarking. We showcase the versatility of our implementation by using it successfully for classification tasks on the MNIST, EMNIST-letters and Fashion MNIST datasets. Through simulations, we show that within an ELM with a sufficient number of parameters, the performance reached using the STVO dynamics as a source of nonlinearity is equivalent to the ones obtained with classical software activation functions such as the reLU and the sigmoid. While achieving state-of-the-art accuracy levels on the MNIST dataset, our model's performance on EMNIST-letters and Fashion MNIST is lower due to the simplicity of the network architecture and the increased complexity of the data. We expect that the DD-TEA framework will enable the exploration of deeper and more complex STVO-based architectures, ultimately leading to improved classification accuracy.

cs.CV↗

arXiv2024

Geometrical properties of 3D crossed nanowire networks

Three-dimensional interconnected nanowire networks have recently attracted notable attention for the fabrication of new devices for energy harvesting/storage, sensing, catalysis, magnetic and spintronic applications and for the design of new hardware neuromorphic computing architectures. However, the complex branching of these nanowire networks makes it challenging to investigate these 3D nanostructured systems theoretically. Here, we present a theoretical description and simulations of the geometric properties of these 3D interconnected nanowire networks with selected characteristics. Our analysis reveals that the nanowire segment length between two crossing zones follows an exponential distribution. This suggests that shorter nanowire segments have a more pronounced influence on the nanowire network properties compared to their longer counterparts. Moreover, our observations reveal a homogeneous distribution in the smallest distance between the cores of two crossing nanowires. The results are highly reproducible and unaffected by changes in the nanowire network characteristics. The density of crossing zones and interconnected nanowire segments are found to vary as the square of the nanowire density multiplied by their diameter, further multiplied by a factor dependent on the packing factor. Finally, densities of interconnected segments up to 10$^{13}$ cm$^{-2}$ can be achieved for 22-$μ$m-thick nanowire networks with high packing factors. This has important implications for neuromorphic computing applications, suggesting that the realization of 10$^{14}$ interconnections, which corresponds to the approximate number of synaptic connections in the human brain, is achievable with a nanowire network of about 10 cm$^{2}$.

physics.app-ph↗

arXiv2023

Current-controlled periodic double-polarity reversals in a spin-torque vortex oscillator

Micromagnetic simulations are used to study a spin-torque vortex oscillator excited by an out-of-plane dc current. The vortex core gyration amplitude is confined between two orbits due to periodical vortex core polarity reversals. The upper limit corresponds to the orbit where the vortex core reaches its critical velocity triggering the first polarity reversal which is immediately followed by a second one. After this double polarity reversal, the vortex core is on a smaller orbit that defines the lower limit of the vortex core gyration amplitude. This double reversal process is a periodic phenomenon and its frequency as well as the upper and lower limits of the vortex core gyration are controlled by the input current density while the vortex chirality determines the onset of this confinement regime. In this non-linear regime, the vortex core never reaches a stable orbit and thus, it may be of interest for neuromorphic application, for example as a leaky integrate-and-fire neuron.

cond-mat.mes-hall↗

arXiv2023

Neuromorphic spintronics simulated using an unconventional data-driven Thiele equation approach

In this study, we developed a quantitative description of the dynamics of spin-torque vortex nano-oscillators (STVOs) through an unconventional model based on the combination of the Thiele equation approach (TEA) and data from micromagnetic simulations (MMS). Solving the STVO dynamics with our analytical model allows to accelerate the simulations by 9 orders of magnitude compared to MMS while reaching the same level of accuracy. Here, we showcase our model by simulating a STVO-based neural network for solving a classification task. We assess its performance with respect to the input signal current intensity and the level of noise that might affect such a system. Our approach is promising for accelerating the design of STVO-based neuromorphic computing devices while decreasing drastically its computational cost.

cs.CV↗

arXiv2023

Neuromorphic spintronics accelerated by an unconventional data-driven Thiele equation approach

We design a neural network based on a single spin-torque vortex nano-oscillator (STVO) multiplexed in time. The behavior of the STVO is simulated with an improved ultra-fast and quantitative model based on the Thiele equation approach. Different mathematical and numerical adaptations are brought to the model in order to increase the accuracy and the speed of the simulations. We demonstrate the high added value and adaptability of such a neural network through the resolution of three standard machine learning tasks in the framework of reservoir computing. The first one is a task of waveform (sines and squares) classification. We show the ability of the system to effectively classify waveforms with high accuracy and low root-mean-square error thanks to the intrinsic short-term memory of the device. Given the high throughput of the simulations, two innovative parametric studies on the intensity of the input signal and the level of noise in the system are performed to demonstrate the value of our new models. The efficiency of our system is then tested during a speech recognition task on the TI-46 dataset and shows the agreement between the new models and the corresponding experimental measurements. Finally, we use our STVO-based neural network to perform image recognition on the MNIST dataset. State-of-the-art performances are demonstrated, and the interest of using the STVO dynamics as an activation function is highlighted. These results support and facilitate the future development of neuromorphic STVO-based hardware for energy-efficient machine learning.

cs.ET↗