arXiv subjects

Anas Skalli

Publications and source records attributed to Anas Skalli.

11 recordsLinked to original sources

arXiv2026

Physical Reservoir Signal Acquisition for Sub-Nyquist Waveform Reconstruction

Physical reservoir computing has traditionally exploited the dynamics of physical systems for computation, enabling tasks such as inference, classification, and prediction. Here, we introduce a fundamentally different paradigm for exploiting physical reservoirs, termed "reservoir signal acquisition" (RSA), in which a physical reservoir serves as a dynamical measurement device rather than a computational engine. In RSA, the reservoir transforms an unknown broadband waveform into a diverse set of measurements, enabling waveform reconstruction from low-rate samples beyond the Nyquist limit of any individual acquisition channel. We show that exact reconstruction of arbitrary broadband signals is achieved when the number of measurement channels satisfies $M \geq N_R$, where $N_R$ is the undersampling ratio. Moreover, spectrally or temporally sparse signals can be recovered even when $M \ll N_R$, demonstrating a compressed-sensing capability that naturally emerges from the diversity of reservoir dynamics. We experimentally validate RSA using a silicon photonic reservoir circuit. With a data-driven calibration requiring no physical model of the device, we reconstruct radio-frequency signals up to 12.5 GHz using only low-rate analog-to-digital converters (ADCs), corresponding to four times the Nyquist frequency of each ADC. These results establish RSA as a new signal acquisition paradigm based on physical reservoirs, extending their role from computation to sub-Nyquist acquisition of broadband waveforms.

cs.ET↗

arXiv2026

Power law scaling for classification accuracy in physical neural networks

Physical neural networks (PNNs) harness the intrinsic complexity of physical systems to perform neural computation, potentially at speeds and energy efficiencies inaccessible to conventional digital hardware. Yet, a principled framework for quantifying and predicting their computing accuracy across diverse substrates has remained elusive. Here we introduce the Hotelling Trace Criterion (HTC), a task-conditioned measure of PNN- state separability that can be evaluated without training. We demonstrate that it predicts PNN classification performance with high fidelity across highly nonlinear optical fibres, vertical-cavity surface-emitting lasers, and coupled nonlinear oscillator networks, for benchmark tasks of different difficulty. Classification loss follows a power law in HTC, with Pearson correlation coefficients exceeding 0.99 for MNIST and $\approx$0.97 for Fashion-MNIST, noteworthy experimental and simulated data from physically distinct systems collapse onto a single scaling curve determined by the task rather than the substrate. Applying HTC layer-by-layer during training further reveals that gradient-based optimisation distributes representational capacity unevenly across PNN layers, providing a quantitative diagnostic of training and architecture efficiency invisible to standard loss monitoring. Crucially, once the scaling exponent is established from a small number of trained calibration systems, all further performance predictions require no training since performance can be derived from the much more efficient HTC measurement. These results establish HTC as a substrate-agnostic figure of merit for comparing and scaling PNNs, advancing the field further towards a complete theory connecting fundamental hardware parameters to task performance through universal scaling laws.

cs.ET↗

arXiv2026

The thin line for optical neural networks towards broad practical relevance

Optical neural networks promise unmatched efficiency, bandwidth, and latency, critical benefits as demand for neural network hardware surges. However, their practical value for general-purpose acceleration or specialized applications must be proven under application-realistic conditions. We discuss recent insights and outline key research priorities.

physics.optics↗

arXiv2025

Model-free front-to-end training of a large high performance laser neural network

Artificial neural networks (ANNs), have become ubiquitous and revolutionized many applications ranging from computer vision to medical diagnoses. However, they offer a fundamentally connectionist and distributed approach to computing, in stark contrast to classical computers that use the von Neumann architecture. This distinction has sparked renewed interest in developing unconventional hardware to support more efficient implementations of ANNs, rather than merely emulating them on traditional systems. Photonics stands out as a particularly promising platform, providing scalability, high speed, energy efficiency, and the ability for parallel information processing. However, fully realized autonomous optical neural networks (ONNs) with in-situ learning capabilities are still rare. In this work, we demonstrate a fully autonomous and parallel ONN using a multimode vertical cavity surface emitting laser (VCSEL) using off-the-shelf components. Our ONN is highly efficient and is scalable both in network size and inference bandwidth towards the GHz range. High performance hardware-compatible optimization algorithms are necessary in order to minimize reliance on external von Neumann computers to fully exploit the potential of ONNs. As such we present and extensively study several algorithms which are broadly compatible with a wide range of systems. We then apply these algorithms to optimize our ONN, and benchmark them using the MNIST dataset. We show that our ONN can achieve high accuracy and convergence efficiency, even under limited hardware resources. Crucially, we compare these different algorithms in terms of scaling and optimization efficiency in term of convergence time which is crucial when working with limited external resources. Our work provides some guidance for the design of future ONNs as well as a simple and flexible way to train them.

cs.LG↗

arXiv2025

Limits of nonlinear and dispersive fiber propagation for an optical fiber-based extreme learning machine

We report a generalized nonlinear Schr\"odinger equation simulation model of an extreme learning machine (ELM) based on optical fiber propagation. Using the MNIST handwritten digit dataset as a benchmark, we study how accuracy depends on propagation dynamics, as well as parameters governing spectral encoding, readout, and noise. For this dataset and with quantum noise limited input, test accuracies of : over 91% and 93% are found for propagation in the anomalous and normal dispersion regimes respectively. Our results also suggest that quantum noise on the input pulses introduces an intrinsic penalty to ELM performance.

physics.optics↗

arXiv2024

A spiking photonic neural network of 40.000 neurons, trained with rank-order coding for leveraging sparsity

Spiking neural networks are neuromorphic systems that emulate certain aspects of biological neurons, offering potential advantages in energy efficiency and speed by for example leveraging sparsity. While CMOS-based electronic SNN hardware has shown promise, scalability and parallelism challenges remain. Photonics provides a promising platform for SNNs due to the speed of excitable photonic devices standing in as neurons and the parallelism and low-latency of optical signal conduction. Here, we present a photonic SNN comprising 40,000 neurons using off-the-shelf components, including a spatial light modulator and a CMOS camera, enabling scalable and cost-effective implementations for photonic SNN proof of concept studies. The system is governed by a modified Ikeda map, were adding additional inhibitory feedback forcing introduces excitability akin to biological dynamics. Using latency encoding and sparsity, the network achieves 83.5% accuracy on MNIST using 22% of neurons, and 77.5% with 8.5% neuron utilization. Training is performed via liquid state machine concepts combined with the hardware-compatible SPSA algorithm, marking its first use in photonic neural networks. This demonstration integrates photonic nonlinearity, excitability, and sparse computation, paving the way for efficient large-scale photonic neuromorphic systems.

cs.ET↗

arXiv2024

Annealing-inspired training of an optical neural network with ternary weights

Artificial neural networks (ANNs) represent a fundamentally connectionnist and distributed approach to computing, and as such they differ from classical computers that utilize the von Neumann architecture. This has revived research interest in new unconventional hardware to enable more efficient implementations of ANNs rather than emulating them on traditional machines. In order to fully leverage the capabilities of this new generation of ANNs, optimization algorithms that take into account hardware limitations and imperfections are necessary. Photonics represents a particularly promising platform, offering scalability, high speed, energy efficiency, and the capability for parallel information processing. Yet, fully fledged implementations of autonomous optical neural networks (ONNs) with in-situ learning remain scarce. In this work, we propose a ternary weight architecture high-dimensional semiconductor laser-based ONN. We introduce a simple method for achieving ternary weights with Boolean hardware, significantly increasing the ONN's information processing capabilities. Furthermore, we design a novel in-situ optimization algorithm that is compatible with, both, Boolean and ternary weights, and provide a detailed hyperparameter study of said algorithm for two different tasks. Our novel algorithm results in benefits, both in terms of convergence speed and performance. Finally, we experimentally characterize the long-term inference stability of our ONN and find that it is extremely stable with a consistency above 99\% over a period of more than 10 hours, addressing one of the main concerns in the field. Our work is of particular relevance in the context of in-situ learning under restricted hardware resources, especially since minimizing the power consumption of auxiliary hardware is crucial to preserving efficiency gains achieved by non-von Neumann ANN implementations.

cs.ET↗

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↗

arXiv2021

Computational metrics and parameters of an injection-locked large area semiconductor laser for neural network computing

Artificial neural networks have become a staple computing technique in many fields. Yet, they present fundamental differences with classical computing hardware in the way they process information. Photonic implementations of neural network architectures potentially offer fundamental advantages over their electronic counterparts in terms of speed, processing parallelism, scalability and energy efficiency. Scalable and high performance photonic neural networks (PNNs) have been demonstrated, yet they remain scarce. In this work, we study the performance of such a scalable, fully parallel and autonomous PNN based on a large area vertical-cavity surface-emitting laser (LA-VCSEL). We show how the performance varies with different physical parameters, namely, injection wavelength, injection power, and bias current. Furthermore, we link these physical parameters to the general computational measures of consistency and dimensionality. We present a general method of gauging dimensionality in high dimensional nonlinear systems subject to noise, which could be applied to many systems in the context of neuromorphic computing. Our work will inform future implementations of spatially multiplexed VCSEL PNNs.

cs.ET↗

arXiv2021

Photonic neuromorphic computing using vertical cavity semiconductor lasers

Photonic realizations of neural network computing hardware are a promising approach to enable future scalability of neuromorphic computing. In this review we provide an overview on vertical-cavity surface-emitting lasers (VCSELs) and how these high-performance electro-optical components either implement or are combined with additional photonic hardware to demonstrate points (i-iii). In the neurmorphic photonics' context, VCSELs are of exceptional interest as they are compatible with CMOS fabrication, readily achieve 30\% wall-plug efficiency and >30~GHz modulation bandwidth and hence are highly energy efficient and ultra-fast. Crucially, they react highly nonlinear to optical injection as well as to electrical modulation, making them highly suitable as all-optical as well as electro-optical photonic neurons. Their optical cavities are wavelength-limited, and standard semiconductor growth and lithography enables non-classical cavity configurations and geometries. This enables excitable VCSELs (i.e. spiking VCSELs) to finely control their temporal and spatial coherence, to unlock Terahertz bandwidths through spin-flip effects, and even to leverage cavity quantum electrodynamics to further boost their efficiency. Finally, as VCSEL arrays they are compatible with standard 2D photonic integration, but their emission vertical to the substrate makes them ideally suited for scalable integrated networks leveraging 3D photonic waveguides. Here, we discuss the implementation of spatially as well as temporally multiplexed VCSEL neural networks and reservoirs, computation on the basis of excitable VCSELs as photonic spiking neurons, as well as concepts and advances in the fabrication of VCSELs and microlasers.

cs.ET↗

arXiv2020

A complete, parallel and autonomous photonic neural network in a semiconductor multimode laser

Neural networks are one of the disruptive computing concepts of our time. However, they fundamentally differ from classical, algorithmic computing in a number of fundamental aspects. These differences result in equally fundamental, severe and relevant challenges for neural network computing using current computing substrates. Neural networks urge for parallelism across the entire processor and for a co-location of memory and arithmetic, i.e. beyond von Neumann architectures. Parallelism in particular made photonics a highly promising platform, yet until now scalable and integratable concepts are scarce. Here, we demonstrate for the first time how a fully parallel and fully implemented photonic neural network can be realized using spatially distributed modes of an efficient and fast semiconductor laser. Importantly, all neural network connections are realized in hardware, and our processor produces results without pre- or post-processing. 130+ nodes are implemented in a large-area vertical cavity surface emitting laser, input and output weights are realized via the complex transmission matrix of a multimode fiber and a digital micro-mirror array, respectively. We train the readout weights to perform 2-bit header recognition, a 2-bit XOR and 2-bit digital analog conversion, and obtain < 0.9 10^-3 and 2.9 10^-2 error rates for digit recognition and XOR, respectively. Finally, the digital analog conversion can be realized with a standard deviation of only 5.4 10^-2. Our system is scalable to much larger sizes and to bandwidths in excess of 20 GHz.

cs.NE↗