Related papers: Comparison of Models for Training Optical Matrix M…
Photonic integrated circuits are facilitating the development of optical neural networks, which have the potential to be both faster and more energy efficient than their electronic counterparts since optical signals are especially…
We demonstrate transfer learning-assisted neural network models for optical matrix multipliers with scarce measurement data. Our approach uses <10\% of experimental data needed for best performance and outperforms analytical models for a…
We present and experimentally evaluate using transfer learning to address experimental data scarcity when training neural network (NN) models for Mach-Zehnder interferometer mesh-based optical matrix multipliers. Our approach involves…
Programming photonic integrated hardware often reveals as a challenging task because of the presence of non-idealities in the photonic chip. These include fabrication imper- fections and parasitic effects such as thermal crosstalk, which…
Mach-Zehnder Interferometric meshes are attractive for low-loss photonic matrix multiplication but are challenging to program. Using least-squares optimization of directional derivatives, we experimentally demonstrate that desired matrix…
Photonic integrated circuits play an important role in the field of optical computing, promising faster and more energy-efficient operations compared to their digital counterparts. This advantage stems from the inherent suitability of…
We demonstrate that networks of locally connected processing units with a primitive learning capability exhibit behavior that is usually only attributed to quantum systems. We describe networks that simulate single-photon beam-splitter and…
Optical neural networks (ONNs) based on programmable photonic integrated circuits (PICs) offer a promising route toward low-latency and energy-efficient deep learning. However, conventional photonic implementations of matrix-vector…
Despite the successful implementations of physics-informed neural networks in different scientific domains, it has been shown that for complex nonlinear systems, achieving an accurate model requires extensive hyperparameter tuning, network…
Recent research has demonstrated the usefulness of neural networks as variational ansatz functions for quantum many-body states. However, high-dimensional sampling spaces and transient autocorrelations confront these approaches with a…
Model Predictive Controllers (MPC) are widely used for controlling cyber-physical systems. It is an iterative process of optimizing the prediction of the future states of a robot over a fixed time horizon. MPCs are effective in practice,…
General-purpose programmable photonic processors offer a flexible foundation for integrating various functionalities within a single chip. A two-dimensional hexagonal waveguide mesh of Mach Zehnder interferometers has been shown to have…
Liquid-fabric interaction simulations using particle-in-cell (PIC) based models have been used to simulate a wide variety of phenomena and yield impressive visual results. However, these models suffer from numerical damping due to the data…
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…
With electric power systems becoming more compact and increasingly powerful, the relevance of thermal stress especially during overload operation is expected to increase ceaselessly. Whenever critical temperatures cannot be measured…
Neural Networks (NN) has been used in many areas with great success. When a NN's structure (Model) is given, during the training steps, the parameters of the model are determined using an appropriate criterion and an optimization algorithm…
Neuromorphic (brain-inspired) photonics leverages photonic chips to accelerate artificial intelligence, offering high-speed and energy efficient solutions in RF communication, tensor processing, and data classification. However, the limited…
Multimode fiber (MMF) imaging aided by machine learning holds promise for numerous applications, including medical endoscopy. A key challenge for this technology is the sensitivity of modal transmission characteristics to environmental…
Machine learning methods have revolutionized the discovery process of new molecules and materials. However, the intensive training process of neural networks for molecules with ever-increasing complexity has resulted in exponential growth…
Growing application space in optical communications, computing, and sensing continues to drive the need for high-performance integrated photonic components. Designing these on-chip systems with complex and application-specific functionality…