Related papers: An array of microresonators as a Photonic Extreme …
Modern deep learning relies nearly exclusively on dedicated electronic hardware accelerators. Photonic approaches, with low consumption and high operation speed, are increasingly considered for inference but, to date, remain mostly limited…
Machine learning is becoming a widely used technique with a impressive growth due to the diversity of problem of societal interest where it can offer practical solutions. This increase of applications and required resources start to become…
The recognition ability of human beings is developed in a progressive way. Usually, children learn to discriminate various objects from coarse to fine-grained with limited supervision. Inspired by this learning process, we propose a simple…
Image-generating machine learning models are typically trained with loss functions based on distance in the image space. This often leads to over-smoothed results. We propose a class of loss functions, which we call deep perceptual…
A meta-model is trained on a distribution of similar tasks such that it learns an algorithm that can quickly adapt to a novel task with only a handful of labeled examples. Most of current meta-learning methods assume that the meta-training…
A method to design gratings in integrated photonics, is presented. The method is based on a transfer matrix formalism enhanced by Finite Element Method (FEM) parameter calculations. The main advantages of the proposed technique are the easy…
The ability to estimate epistemic uncertainty is often crucial when deploying machine learning in the real world, but modern methods often produce overconfident, uncalibrated uncertainty predictions. A common approach to quantify epistemic…
Achieving consistent color reproduction across multiple cameras is essential for seamless image fusion and Image Processing Pipeline (ISP) compatibility in modern devices, but it is a challenging task due to variations in sensors and…
Photonic computing is a computing paradigm which have great potential to overcome the energy bottlenecks of electronic von Neumann architecture. Throughput and power consumption are fundamental limitations of…
Automated experiments in scanning transmission electron microscopy (STEM) require rapid image segmentation to optimize data representation for human interpretation, decision-making, site-selective spectroscopies, and atomic manipulation.…
Deep learning based approaches have achieved significant progresses in different tasks like classification, detection, segmentation, and so on. Ensemble learning is widely known to further improve performance by combining multiple…
Federated Learning (FL) is an emerging paradigm that allows a model to be trained across a number of participants without sharing data. Recent works have begun to consider the effects of using pre-trained models as an initialization point…
Photonic systems for high-performance information processing have attracted renewed interest. Neuromorphic silicon photonics has the potential to integrate processing functions that vastly exceed the capabilities of electronics. We report…
Transfer learning has become crucial in computer vision tasks due to the vast availability of pre-trained deep learning models. However, selecting the optimal pre-trained model from a diverse pool for a specific downstream task remains a…
Prompt learning represents a promising method for adapting pre-trained vision-language models (VLMs) to various downstream tasks by learning a set of text embeddings. One challenge inherent to these methods is the poor generalization…
We investigate end-to-end optimized optical transmission systems based on feedforward or bidirectional recurrent neural networks (BRNN) and deep learning. In particular, we report the first experimental demonstration of a BRNN auto-encoder,…
Machine learning and optimization algorithms have been widely applied in the design and optimization for photonic devices. In this article, we briefly review recent progress of this field of research and show some data-driven applications…
Fine-grained image classification has witnessed significant advancements with the advent of deep learning and computer vision technologies. However, the scarcity of detailed annotations remains a major challenge, especially in scenarios…
We report on the investigation of an approach for modelling light transmission through systems consisting of several jointed optical fibres, in which the analytical modelling of the waveguides was replaced by Finite Element Modelling (FEM)…
Photonic integrated circuits are emerging as a promising platform for accelerating matrix multiplications in deep learning, leveraging the inherent parallel nature of light. Although various schemes have been proposed and demonstrated to…