Related papers: Parity-time symmetric optical neural networks

With recent rapid advances in photonic integrated circuits, it has been demonstrated that programmable photonic chips can be used to implement artificial neural networks. Convolutional neural networks (CNN) are a class of deep learning…

Diffractive deep neural network (DNNet) is a novel machine learning framework on the modulation of optical transmission. Diffractive network would get predictions at the speed of light. It's pure passive architecture, no additional power…

Physics-Informed Neural Networks (PINNs) offer a flexible paradigm for solving differential equations by embedding governing laws into the training objective. A persistent limitation is instance specificity: standard PINNs typically require…

One of the most exciting advancements in AI over the last decade is the wide adoption of ANNs, such as DNN and CNN, in many real-world applications. However, the underlying massive amounts of computation and storage requirement greatly…

Optimal transmission switching (OTS) improves optimal power flow (OPF) by selectively opening transmission lines, but its mixed-integer formulation increases computational complexity, especially on large grids. To address this, we propose a…

This paper addresses the limitations in Optical Neural Networks (ONNs) related to training efficiency, nonlinear function implementation, and large input data processing. We introduce Two-Pass Forward Propagation, a novel training method…

Learning based approaches have not yet achieved their full potential in optical flow estimation, where their performance still trails heuristic approaches. In this paper, we present a CNN based patch matching approach for optical flow…

Embedded deep learning platforms have witnessed two simultaneous improvements. First, the accuracy of convolutional neural networks (CNNs) has been significantly improved through the use of automated neural-architecture search (NAS)…

Recently, spiking neural networks (SNNs), deployed on neuromorphic chips, provide highly efficient solutions on edge devices in different scenarios. However, their ability to adapt to distribution shifts after deployment has become a…

The focus of our work is speeding up evaluation of deep neural networks in retrieval scenarios, where conventional architectures may spend too much time on negative examples. We propose to replace a monolithic network with our novel cascade…

Spiking Neural Network (SNN), as a brain-inspired and energy-efficient network, is currently facing the pivotal challenge of exploring a suitable and efficient learning framework. The predominant training methodologies, namely…

As deep neural networks (DNNs) grow to solve increasingly complex problems, they are becoming limited by the latency and power consumption of existing digital processors. For improved speed and energy efficiency, specialized analog optical…

The demand for executing Deep Neural Networks (DNNs) with low latency and minimal power consumption at the edge has led to the development of advanced heterogeneous Systems-on-Chips (SoCs) that incorporate multiple specialized computing…

Operator learning enables fast surrogate modeling of high-dimensional dynamical systems, but existing approaches face two fundamental limitations: quadratic inference complexity and unreliable uncertainty quantification in safety-critical…

Spiking neural networks (SNNs) exhibit superior energy efficiency but suffer from limited performance. In this paper, we consider SNNs as ensembles of temporal subnetworks that share architectures and weights, and highlight a crucial issue…

Increasing the layer number of on-chip photonic neural networks (PNNs) is essential to improve its model performance. However, the successively cascading of network hidden layers results in larger integrated photonic chip areas. To address…

ConvNets, through their architecture, only enforce invariance to translation. In this paper, we introduce a new class of deep convolutional architectures called Non-Parametric Transformation Networks (NPTNs) which can learn \textit{general}…

This paper performs a detailed, multi-faceted analysis of key challenges and common design caveats related to the development of efficient neural networks (NN) nonlinear channel equalizers in coherent optical communication systems. Our…

With growing investigations into solving partial differential equations by physics-informed neural networks (PINNs), more accurate and efficient PINNs are required to meet the practical demands of scientific computing. One bottleneck of…

Distributed learning is widely used for training large models on large datasets by distributing parts of the model or dataset across multiple devices and aggregating the computed results for subsequent computations or parameter updates.…