相关论文: Scalability of On-chip Diffractive Optical Neural …

A fundamental task for artificial intelligence is learning. Deep Neural Networks have proven to cope perfectly with all learning paradigms, i.e. supervised, unsupervised, and reinforcement learning. Nevertheless, traditional deep learning…

Atomic systems have long provided a useful material platform with unique quantum properties. The efficient light-matter interaction in atomic vapors has led to numerous seminal scientific achievements including accurate and precise…

Graph Neural Networks (GNNs) are a new and increasingly popular family of deep neural network architectures to perform learning on graphs. Training them efficiently is challenging due to the irregular nature of graph data. The problem…

Deep learning techniques are increasingly applied to scientific problems, where the precision of networks is crucial. Despite being deemed as universal function approximators, neural networks, in practice, struggle to reduce the prediction…

Similar to algorithms, which consume time and memory to run, hardware requires resources to function. For devices processing physical waves, implementing operations needs sufficient "space," as dictated by wave physics. How much space is…

Owing to its potential advantages such as scalability, low latency and power efficiency, optical computing has seen rapid advances over the last decades. A core unit of a potential all-optical processor would be the NAND gate, which can be…

Optical neural network (ONN) is emerging as an attractive proposal for machine-learning applications, enabling high-speed computation with low-energy consumption. However, there are several challenges in applying ONN for industrial…

We present a spiking neural network (SNN) for visual pattern recognition with on-chip learning on neuromorphichardware. We show how this network can learn simple visual patterns composed of horizontal and vertical bars sensed by a Dynamic…

Deep neural networks (DNNs) have shown remarkable performance improvements on vision-related tasks such as object detection or image segmentation. Despite their success, they generally lack the understanding of 3D objects which form the…

Deep neural networks (DNNs) have been widely used in computer vision tasks like image classification, object detection and segmentation. Whereas recent studies have shown their vulnerability to manual digital perturbations or distortion in…

Optical computing is considered a promising solution for the growing demand for parallel computing in various cutting-edge fields, requiring high integration and high speed computational capacity. In this paper, we propose a novel optical…

While binary neural networks (BNNs) offer significant benefits in terms of speed, memory and energy, they encounter substantial accuracy degradation in challenging tasks compared to their real-valued counterparts. Due to the binarization of…

A plethora of research advances have emerged in the fields of optics and photonics that benefit from harnessing the power of machine learning. Specifically, there has been a revival of interest in optical computing hardware, due to its…

Machine intelligence, especially using convolutional neural networks (CNNs), has become a large area of research over the past years. Increasingly sophisticated hardware accelerators are proposed that exploit e.g. the sparsity in…

Computing with coupled oscillators or oscillatory neural networks (ONNs) has recently attracted a lot of interest due to their potential for massive parallelism and energy-efficient computing. However, to date, ONNs have primarily been…

Having the potential for high speed, high throughput, and low energy cost, optical neural networks (ONNs) have emerged as a promising candidate for accelerating deep learning tasks. In conventional ONNs, light amplitudes are modulated at…

A cascaded phase-only mask architecture (or an optical diffractive neural network) can be employed for different optical information processing tasks such as pattern recognition, orbital angular momentum (OAM) mode conversion, image…

Deep learning is one of the most advancing technologies in various fields. Facing the limits of the current electronics platform, optical neural networks (ONNs) based on Si programmable photonic integrated circuits (PICs) have attracted…

Inspired by the connectivity mechanisms in the brain, neuromorphic computing architectures model Spiking Neural Networks (SNNs) in silicon. As such, neuromorphic architectures are designed and developed with the goal of having small, low…

Diffraction drastically limits the bit density in optical data storage. To increase the storage density, alternative strategies involving supplementary recording dimensions and robust read-out schemes must be explored. Here, we propose to…