Photonic Neural Networks (PNNs) can accelerate machine learning workloads by implementing Matrix-Vector Multiplications (MVMs) in integrated photonic circuits, but existing simulation and training frameworks scale poorly to large Photonic Unitary Matrix (PUM) meshes because they explicitly construct and manipulate dense transfer matrices. This work introduces the Slicing method, which models PUM meshes as sequences of local 2×2 operations organized into computational windows and computes forward and backward propagation using only localized matrix℄vector updates with linear complexity in the number of active cells. The method is implemented in LuxIA, an open-source PyTorch-based framework for end-to-end PNN simulation and training that supports multiple mesh architectures and datasets. A formal analysis shows that Slicing reduces perpass work by one degree (from quartic to cubic) in the worstcase. Experiments on Clements, Fldzhyan, and Bell-optimized meshes trained on Iris, Digits, MNIST, and Olivetti Faces show that LuxIA matches the training dynamics and task accuracy of existing tools while substantially improving training efficiency: on large meshes and batches, LuxIA achieves up to 4.7× lower training time and more than an order-of-magnitude reduction in Graphics Processing Unit (GPU) memory compared with conventional transfer-matrix frameworks, and it remains within the memory budget where competing tools fail.

In this work, we discuss our vision for neuromorphic accelerators based on integrated photonics within the framework of the Horizon Europe NEUROPULS project. Augmented integrated photonic architectures that leverage phase-change and III-V materials for optical computing will be presented. A CMOS-compatible platform will be discussed that integrates these materials to fabricate photonic neuromorphic architectures, along with a gem5-based simulation platform to model accelerator operation once it is interfaced with a RISC-V processor. This simulation platform enables accurate system-level accelerator modeling and benchmarking in terms of key metrics such as speed, energy consumption, and footprint.

This special session paper introduces the Horizon Europe NEUROPULS project, which targets the development of secure and energy-efficient RISC-V interfaced neuromorphic accelerators using augmented silicon photonics technology. Our approach aims to develop an augmented silicon photonics platform, an FPGA-powered RISC-V-connected computing platform, and a complete simulation platform to demonstrate the neuromorphic accelerator capabilities. In particular, their main advantages and limitations will be addressed concerning the underpinning technology for each platform. Then, we will discuss three targeted use cases for edge-computing applications: Global National Satellite System (GNSS) anti-jamming, autonomous driving, and anomaly detection in edge devices. Finally, we will address the reliability and security aspects of the stand-alone accelerator implementation and the project use cases.

The field of neuromorphic computing has been rapidly evolving in recent years, with an increasing focus on hardware design and reliability. This special session paper provides an overview of the recent developments in neuromorphic computing, focusing on hardware design and reliability. We first review the traditional CMOS-based approaches to neuromorphic hardware design and identify the challenges related to scalability, latency, and power consumption. We then investigate alternative approaches based on emerging technologies, specifically integrated photonics approaches within the NEUROPULS project. Finally, we examine the impact of device variability and aging on the reliability of neuromorphic hardware and present techniques for mitigating these effects. This review is intended to serve as a valuable resource for researchers and practitioners in neuromorphic computing.

As Moore's law comes to an end, neuromorphic approaches to computing are on the rise. One of these, passive photonic reservoir computing, is a strong candidate for computing at high bitrates (>10 Gb/s) and with low energy consumption. Currently though, both benefits are limited by the necessity to perform training and readout operations in the electrical domain. Thus, efforts are currently underway in the photonic community to design an integrated optical readout, which allows to perform all operations in the optical domain. In addition to the technological challenge of designing such a readout, new algorithms have to be designed in order to train it. Foremost, suitable algorithms need to be able to deal with the fact that the actual on-chip reservoir states are not directly observable. In this paper, we investigate several options for such a training algorithm and propose a solution in which the complex states of the reservoir can be observed by appropriately setting the readout weights, while iterating over a predefined input sequence. We perform numerical simulations in order to compare our method with an ideal baseline requiring full observability as well as with an established black-box optimization approach (CMA-ES).

Reservoir computing (RC) is a computing scheme related to recurrent neural network theory. As a model for neural activity in the brain, it attracts a lot of attention, especially because of its very simple training method. However, building a functional, on-chip, photonic implementation of RC remains a challenge. Scaling delay lines down from optical fiber scale to chip scale results in RC systems that compute faster, but at the same time requires that the input signals be scaled up in speed, which might be impractical or expensive. In this brief, we show that this problem can be alleviated by a masked RC system in which the amplitude of the input signal is modulated by a binary-valued mask. For a speech recognition task, we demonstrate that the necessary input sample rate can be a factor of 40 smaller than in a conventional RC system. In addition, we also show that linear discriminant analysis and input matrix optimization is a well-performing alternative to linear regression for reservoir training.

Delay-coupled optoelectronic systems form promising candidates to act as powerful information processing devices. In this brief, we consider such a system that has been studied before in the context of reservoir computing (RC). Instead of viewing the system as a random dynamical system, we see it as a true machine-learning model, which can be fully optimized. We use a recently introduced extension of backpropagation through time, an optimization algorithm originally designed for recurrent neural networks, and use it to let the network perform a difficult phoneme recognition task. We show that full optimization of all system parameters of delay-coupled optoelectronics systems yields a significant improvement over the previously applied RC approach.

Reservoir computing (RC) is a technique in machine learning inspired by neural systems. RC has been used successfully to solve complex problems such as signal classification and signal generation. These systems are mainly implemented in software, and thereby they are limited in speed and power efficiency. Several optical and optoelectronic implementations have been demonstrated, in which the system has signals with an amplitude and phase. It is proven that these enrich the dynamics of the system, which is beneficial for the performance. In this paper, we introduce a novel optical architecture based on nanophotonic crystal cavities. This allows us to integrate many neurons on one chip, which, compared with other photonic solutions, closest resembles a classical neural network. Furthermore, the components are passive, which simplifies the design and reduces the power consumption. To assess the performance of this network, we train a photonic network to generate periodic patterns, using an alternative online learning rule called first-order reduced and corrected error. For this, we first train a classical hyperbolic tangent reservoir, but then we vary some of the properties to incorporate typical aspects of a photonics reservoir, such as the use of continuous-time versus discrete-time signals and the use of complex-valued versus real-valued signals. Then, the nanophotonic reservoir is simulated and we explore the role of relevant parameters such as the topology, the phases between the resonators, the number of nodes that are biased and the delay between the resonators. It is important that these parameters are chosen such that no strong self-oscillations occur. Finally, our results show that for a signal generation task a complex-valued, continuous-time nanophotonic reservoir outperforms a classical (i.e., discrete-time, real-valued) leaky hyperbolic tangent reservoir (normalized root-mean-square errors=0.030 versus NRMSE=0.127).

Reservoir computing (RC), a computational paradigm inspired on neural systems, has become increasingly popular in recent years for solving a variety of complex recognition and classification problems. Thus far, most implementations have been software-based, limiting their speed and power efficiency. Integrated photonics offers the potential for a fast, power efficient and massively parallel hardware implementation. We have previously proposed a network of coupled semiconductor optical amplifiers as an interesting test case for such a hardware implementation. In this paper, we investigate the important design parameters and the consequences of process variations through simulations. We use an isolated word recognition task with babble noise to evaluate the performance of the photonic reservoirs with respect to traditional software reservoir implementations, which are based on leaky hyperbolic tangent functions. Our results show that the use of coherent light in a well-tuned reservoir architecture offers significant performance benefits. The most important design parameters are the delay and the phase shift in the system's physical connections. With optimized values for these parameters, coherent semiconductor optical amplifier (SOA) reservoirs can achieve better results than traditional simulated reservoirs. We also show that process variations hardly degrade the performance, but amplifier noise can be detrimental. This effect must therefore be taken into account when designing SOA-based RC implementations.

We investigate the possibility to achieve band-edge lasing in optically thick gold-clad photonic-crystal (PhC) membranes, with a dielectric thickness of around 1 /spl mu/m. We have performed a two-dimensional eigenmode-expansion analysis of band-edge resonators in one-dimensional PhCs. Material thresholds, quality factors, and emission efficiencies have been calculated for TE band-edge laser resonances on the second and third /spl Gamma/-point. The second /spl Gamma/-point sustains band-edge laser modes with quality factors above 2500 for a membrane thickness of 1 /spl mu/m and a cavity length of 20 periods, however, with a very poor surface-emission efficiency. Band-edge laser modes located on the third /spl Gamma/-point have lower quality factors but higher surface-emission efficiencies. In both cases, the PhC should be designed specifically to avoid coupling with lossy, higher order modes.