Related papers: Polarization Multiplexed Diffractive Computing: Al…

In the framework of convolutional neural networks that lie at the heart of deep learning, downsampling is often performed with a max-pooling operation that only retains the element with maximum activation, while completely discarding the…

Data center networks are experiencing unprecedented exponential growth, mostly driven by the continuous computing demands in machine learning and artificial intelligence algorithms. Within this realm, optical networking offers numerous…

Structural coloration is commonly modeled using wave optics for reliable and photorealistic rendering of natural, quasi-periodic and complex nanostructures. Such models often rely on dense, preliminary or preprocessed data to accurately…

Semantic segmentation and lane detection are crucial tasks in autonomous driving systems. Conventional approaches predominantly rely on deep neural networks (DNNs), which incur high energy costs due to extensive analog-to-digital…

Programmable photonic integrated circuits represent an emerging technology that amalgamates photonics and electronics, paving the way for light-based information processing at high speeds and low power consumption. Considering their wide…

Behavior of neural networks is irremediably determined by the specific loss and data used during training. However it is often desirable to tune the model at inference time based on external factors such as preferences of the user or…

Particle filtering is a powerful approach to sequential state estimation and finds application in many domains, including robot localization, object tracking, etc. To apply particle filtering in practice, a critical challenge is to…

Multimode fibres (MMF) are remarkable high-capacity information channels owing to the large number of transmitting fibre modes, and have recently attracted significant renewed interest in applications such as optical communication, imaging,…

Optics and photonics has recently captured interest as a platform to accelerate linear matrix processing, that has been deemed as a bottleneck in traditional digital electronic architectures. In this paper, we propose an all-photonic…

In contrast to software simulations of neural networks, hardware implementations have often limited or no tunability. While such networks promise great improvements in terms of speed and energy efficiency, their performance is limited by…

Multimode optical fibers have seen increasing applications in communication, imaging, high-power lasers and amplifiers. However, inherent imperfections and environmental perturbations cause random polarization and mode mixing, making the…

An optical diffractive neural network (DNN) can be implemented with a cascaded phase mask architecture. Like an optical computer, the system can perform machine learning tasks such as number digit recognition in an all-optical manner.…

Recent studies have shown that a Deep Convolutional Neural Network (DCNN) pretrained on a large image dataset can be used as a universal image descriptor, and that doing so leads to impressive performance for a variety of image…

Pooling operations, which can be calculated at low cost and serve as a linear or nonlinear transfer function for data reduction, are found in almost every modern neural network. Countless modern approaches have already tackled replacing the…

The majority of computer vision algorithms fail to find higher-order (abstract) patterns in an image so are not robust against adversarial attacks, unlike human lateralized vision. Deep learning considers each input pixel in a homogeneous…

Sensing light's polarization and wavefront direction enables surface curvature assessment, material identification, shadow differentiation, and improved image quality in turbid environments. Traditional polarization cameras utilize multiple…

Autonomous synthesis and characterization of inorganic materials requires the automatic and accurate analysis of X-ray diffraction spectra. For this task, we designed a probabilistic deep learning algorithm to identify complex multi-phase…

Although deep learning has achieved remarkable success in various scientific machine learning applications, its opaque nature poses concerns regarding interpretability and generalization capabilities beyond the training data.…

We report an in-silico demonstration of an all-optical cell classification system using a single-layer diffractive neural network (DNN) optimized for real-world biomedical images. Implemented virtually with a spatial light modulator (SLM),…

In optical imaging, light propagation is affected by the inhomogeneities of the medium. Sample-induced aberrations and multiple scattering can strongly degrade the image resolution and contrast. Based on a dynamic correction of the incident…