In our experiments, the proposed method achieved a test classification accuracy of 96.5%

The enormous energy demand of artificial intelligence is driving the development of alternative hardware for deep learning. Physical neural networks try to exploit physical systems to perform machine learning more efficiently. In particular, optical systems can calculate with light using negligible energy. While their computational capabilities were long limited by the linearity of optical materials, nonlinear computations have recently been demonstrated through modified input encoding. Despite this breakthrough, our inability to determine if physical neural networks can learn arbitrary relationships between data -- a key requirement for deep learning known as universality -- hinders further progress. Here we present a fundamental theorem that establishes a universality condition for physical neural networks. It provides a powerful mathematical criterion that imposes device constraints, detailing how inputs should be encoded in the tunable parameters of the physical system. Based on this result, we propose a scalable architecture using free-space optics that is provably universal and achieves high accuracy on image classification tasks. Further, by combining the theorem with temporal multiplexing, we present a route to potentially huge effective system sizes in highly practical but poorly scalable on-chip photonic devices. Our theorem and scaling methods apply beyond optical systems and inform the design of a wide class of universal, energy-efficient physical neural networks, justifying further efforts in their development.

Hybrid Optical Neural Networks (ONNs, typically consisting of an optical frontend and a digital backend) offer an energy-efficient alternative to fully digital deep networks for real-time, power-constrained systems. However, their adoption is limited by two main challenges: the accuracy gap compared to large-scale networks during training, and discrepancies between simulated and fabricated systems that further degrade accuracy. While previous work has proposed end-to-end optimizations for specific datasets (e.g., MNIST) and optical systems, these approaches typically lack generalization across tasks and hardware designs. To address these limitations, we propose a task-agnostic and hardware-agnostic pipeline that supports image classification and segmentation across diverse optical systems. To assist optical system design before training, we estimate achievable model accuracy based on user-specified constraints such as physical size and the dataset. For training, we introduce Neural Tangent Knowledge Distillation (NTKD), which aligns optical models with electronic teacher networks, thereby narrowing the accuracy gap. After fabrication, NTKD also guides fine-tuning of the digital backend to compensate for implementation errors. Experiments on multiple datasets (e.g., MNIST, CIFAR, Carvana Masking) and hardware configurations show that our pipeline consistently improves ONN performance and enables practical deployment in both pre-fabrication simulations and physical implementations.

Ray tracing is a widely used technique for modeling optical systems, involving sequential surface-by-surface computations, which can be computationally intensive. We propose Ray2Ray, a novel method that leverages implicit neural representations to model optical systems with greater efficiency, eliminating the need for surface-by-surface computations in a single pass end-to-end model. Ray2Ray learns the mapping between rays emitted from a given source and their corresponding rays after passing through a given optical system in a physically accurate manner. We train Ray2Ray on nine off-the-shelf optical systems, achieving positional errors on the order of 1μm and angular deviations on the order 0.01 degrees in the estimated output rays. Our work highlights the potential of neural representations as a proxy for optical raytracer.

In the rapidly evolving field of optical engineering, precise alignment of multi-lens imaging systems is critical yet challenging, as even minor misalignments can significantly degrade performance. Traditional alignment methods rely on specialized equipment and are time-consuming processes, highlighting the need for automated and scalable solutions. We present two complementary deep learning-based inverse-design methods for diagnosing misalignments in multi-element lens systems using only optical measurements. First, we use ray-traced spot diagrams to predict five-degree-of-freedom (5-DOF) errors in a 6-lens photographic prime, achieving a mean absolute error of 0.031mm in lateral translation and 0.011$^\circ$ in tilt. We also introduce a physics-based simulation pipeline that utilizes grayscale synthetic camera images, enabling a deep learning model to estimate 4-DOF, decenter and tilt errors in both two- and six-lens multi-lens systems. These results show the potential to reshape manufacturing and quality control in precision imaging.

Aligning a lens system relative to an imager is a critical challenge in camera manufacturing. While optimal alignment can be mathematically computed under ideal conditions, real-world deviations caused by manufacturing tolerances often render this approach impractical. Measuring these tolerances can be costly or even infeasible, and neglecting them may result in suboptimal alignments. We propose a reinforcement learning (RL) approach that learns exclusively in the pixel space of the sensor output, eliminating the need to develop expert-designed alignment concepts. We conduct an extensive benchmark study and show that our approach surpasses other methods in speed, precision, and robustness. We further introduce relign, a realistic, freely explorable, open-source simulation utilizing physically based rendering that models optical systems with non-deterministic manufacturing tolerances and noise in robotic alignment movement. It provides an interface to popular machine learning frameworks, enabling seamless experimentation and development. Our work highlights the potential of RL in a manufacturing environment to enhance efficiency of optical alignments while minimizing the need for manual intervention.

This paper introduces a differentiable ray-tracing based model that incorporates aberrations and distortions to render realistic coded hyperspectral acquisitions using Coded-Aperture Spectral Snapshot Imagers (CASSI). CASSI systems can now be optimized in order to fulfill simultaneously several optical design constraints as well as processing constraints. Four comparable CASSI systems with varying degree of optical aberrations have been designed and modeled. The resulting rendered hyperspectral acquisitions from each of these systems are combined with five state-of-the-art hyperspectral cube reconstruction processes. These reconstruction processes encompass a mapping function created from each system's propagation model to account for distortions and aberrations during the reconstruction process. Our analyses show that if properly modeled, the effects of geometric distortions of the system and misalignments of the dispersive elements have a marginal impact on the overall quality of the reconstructed hyperspectral data cubes. Therefore, relaxing traditional constraints on measurement conformity and fidelity to the scene enables the development of novel imaging instruments, guided by performance metrics applied to the design or the processing of acquisitions. By providing a complete framework for design, simulation and evaluation, this work contributes to the optimization and exploration of new CASSI systems, and more generally to the computational imaging community.

The ability to train ever-larger neural networks brings artificial intelligence to the forefront of scientific and technical discoveries. However, their exponentially increasing size creates a proportionally greater demand for energy and computational hardware. Incorporating complex physical events in networks as fixed, efficient computation modules can address this demand by decreasing the complexity of trainable layers. Here, we utilize ultrashort pulse propagation in multimode fibers, which perform large-scale nonlinear transformations, for this purpose. Training the hybrid architecture is achieved through a neural model that differentiably approximates the optical system. The training algorithm updates the neural simulator and backpropagates the error signal over this proxy to optimize layers preceding the optical one. Our experimental results achieve state-of-the-art image classification accuracies and simulation fidelity. Moreover, the framework demonstrates exceptional resilience to experimental drifts. By integrating low-energy physical systems into neural networks, this approach enables scalable, energy-efficient AI models with significantly reduced computational demands.

Abstract: The design and performance analysis of relay lenses that provide high-performance image transmission for target acquisition and tracking in military optical systems. Relay lenses are critical components for clear and lossless image transmission over long distances. In this study, the optical performance of a relay lens system designed and optimized using ZEMAX software is investigated in detail. The analysis focuses on important optical properties such as modulation transfer function (MTF), spot diagrams, Seidel diagram, field curvature and distortion. The results show that the lens has significant potential in military applications for target detection and tracking with high resolution and low aberration. Accepted: 1. Introduction Military optical systems provide high-performance and reliable monitoring for target identification and tracking in critical missions. These systems have become indispensable in modern warfare, where the ability to process and analyze real-time visual data can determine the success or failure of operations. By combining advanced optical technologies with robust design methodologies, military systems aim to deliver precise and effective solutions for a variety of applications. In this context, optical components must ensure exceptional image clarity, resolution, and durability to withstand challenging operational environments.