A novel method based on deep learning technique for the modal decomposition of the optical fields emerging from the few-mode fiber is demonstrated in this paper. By combining the advantages of ...principal component analysis (PCA) and Back-Propagation (BP) neural network, this scheme can reveal the exact superposition of eigenmodes. Firstly, PCA algorithm is applied to preprocess the target samples to reduce the computational complexity and extract the characteristics of the samples. Then, the mapping between the mode coefficients and the preprocessed near-field beam patterns is learned by using the BP neural network. The superiority of the proposed scheme is evaluated through simulation and experiment. The results show that the scheme can perform a complete modal decomposition within a few milliseconds, and it can still work well when the SNR level is as low as 20 dB. It is also worth noting that the method described in this work also has the advantages of short network training time, non-iterative, and low experimental equipment requirements.
When using stochastic gradient descent (SGD) to solve large-scale machine learning problems especially deep learning problems, a common practice of data processing is to shuffle the training data, ...partition the data across multiple threads/machines if needed, and then perform several epochs of training on the re-shuffled (either locally or globally) data. The above procedure makes the instances used to compute the gradients no longer independently sampled from the training data set, which contradicts with the basic assumptions of conventional convergence analysis of SGD. Then does the distributed SGD method have desirable convergence properties in this practical situation? In this paper, we give answers to this question. First, we give a mathematical formulation for the practical data processing procedure in distributed machine learning, which we call (data partition with) global/local shuffling. We observe that global shuffling is equivalent to without-replacement sampling if the shuffling operations are independent. Second, we prove SGD with global shuffling and local shuffling has convergence guarantee for non-convex tasks like deep learning. The convergence rate for local shuffling is slower than that for global shuffling, since it will lose some information if there’s no communication between partitioned data. We also consider the situation when the permutation after shuffling is not uniformly distributed (We call it insufficient shuffling), and discuss the condition under which this insufficiency will not influence the convergence rate. Finally, we give the convergence analysis in convex case. An interesting finding is that, the non-convex tasks like deep learning are more suitable to apply shuffling comparing to the convex tasks. Our theoretical results provide important insights to large-scale machine learning, especially in the selection of data processing methods in order to achieve faster convergence and good speedup. Our theoretical findings are verified by extensive experiments on logistic regression and deep neural networks.
A novel bending vector sensor formed by splicing 2-core fiber (2CF) between two segments of multimode fibers (MMFs) was proposed and fabricated, in which the MMFs serve as the mode splitting and ...coupling. Moreover, the 2CF used in the experiment was designed and fabricated in our labs, and the external core with a larger diameter would be provided with a higher bending sensitivity. Besides, the bending responses of the sensor are directionally sensitive due to the asymmetric structure of the 2CF. As a result, along with the implementation of the conformation experiments on the bending and temperature sensor property, and a good agreement has been achieved. The proposed sensor possesses many advantages, such as being inexpensive, compact, and robust.
Artificial intelligence (AI) is being increasingly integrated into scientific discovery to augment and accelerate research, helping scientists to generate hypotheses, design experiments, collect and ...interpret large datasets, and gain insights that might not have been possible using traditional scientific methods alone. Here we examine breakthroughs over the past decade that include self-supervised learning, which allows models to be trained on vast amounts of unlabelled data, and geometric deep learning, which leverages knowledge about the structure of scientific data to enhance model accuracy and efficiency. Generative AI methods can create designs, such as small-molecule drugs and proteins, by analysing diverse data modalities, including images and sequences. We discuss how these methods can help scientists throughout the scientific process and the central issues that remain despite such advances. Both developers and users of AI toolsneed a better understanding of when such approaches need improvement, and challenges posed by poor data quality and stewardship remain. These issues cut across scientific disciplines and require developing foundational algorithmic approaches that can contribute to scientific understanding or acquire it autonomously, making them critical areas of focus for AI innovation.
A two-dimensional bending vector sensor based on the multimode-3-core-multimode fiber structure is proposed. The three cores of the 3-core fiber (3CF) distribute in an isosceles triangle. In order to ...obtain a higher bending sensitivity, two larger diameter external cores are selected in the design of the 3CF. Owing to the asymmetric structure of the 3CF, this sensor can distinguish multiple bending directions. In addition, the linear spectral response for bending and temperature is observed experimentally. The proposed sensor has many advantages. For example, it is compact, inexpensive, and easy to be fabricated. These characteristics of the sensor make it very attractive for two-dimensional bending sensing application.
LETOR is a benchmark collection for the research on learning to rank for information retrieval, released by Microsoft Research Asia. In this paper, we describe the details of the LETOR collection and ...show how it can be used in different kinds of researches. Specifically, we describe how the document corpora and query sets in LETOR are selected, how the documents are sampled, how the learning features and meta information are extracted, and how the datasets are partitioned for comprehensive evaluation. We then compare several state-of-the-art learning to rank algorithms on LETOR, report their ranking performances, and make discussions on the results. After that, we discuss possible new research topics that can be supported by LETOR, in addition to algorithm comparison. We hope that this paper can help people to gain deeper understanding of LETOR, and enable more interesting research projects on learning to rank and related topics.
In this article, we demonstrate a "Fabry-Perot + Michelson" hybrid interferometer based on a polymer micro-cap located on asymmetric 2-core fiber (2CF) facet. Because the polymer micro-cap comprises ...a flat reflector and a concave reflector, the light propagating in the centric core will be reflected twice forming Fabry-Perot interference. Due to the bias angle between the eccentric core and the concave reflector, the light in the eccentric core reflects only once on the flat reflector and would interfere with the other reflected light in the 2CF. The experimental results show that Fabry-Perot and Michelson interference occur and are superimposed on the directly detected spectrum. Independent interferometric spectrums can be separated by Discrete Fourier Transform to achieve humidity-temperature simultaneous measurement based on coefficient matrix demodulation. Moreover, this new optical fiber sensing platform is all-solid, high-integration, and flexible, so it has potential in lab-on-fiber applications.
Conditional Image-to-Image Translation Lin, Jianxin; Xia, Yingce; Qin, Tao ...
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
Conference Proceeding
Odprti dostop
Image-to-image translation tasks have been widely investigated with Generative Adversarial Networks (GANs) and dual learning. However, existing models lack the ability to control the translated ...results in the target domain and their results usually lack of diversity in the sense that a fixed image usually leads to (almost) deterministic translation result. In this paper, we study a new problem, conditional image-to-image translation, which is to translate an image from the source domain to the target domain conditioned on a given image in the target domain. It requires that the generated image should inherit some domain-specific features of the conditional image from the target domain. Therefore, changing the conditional image in the target domain will lead to diverse translation results for a fixed input image from the source domain, and therefore the conditional input image helps to control the translation results. We tackle this problem with unpaired data based on GANs and dual learning. We twist two conditional translation models (one translation from A domain to B domain, and the other one from B domain to A domain) together for inputs combination and reconstruction while preserving domain independent features. We carry out experiments on men's faces from-to women's faces translation and edges to shoes&bags translations. The results demonstrate the effectiveness of our proposed method.
Energy conservation is a basic physics principle, the breakdown of which often implies new physics. This paper presents a method for data-driven "new physics" discovery. Specifically, given a ...trajectory governed by unknown forces, our neural new-physics detector (NNPhD) aims to detect new physics by decomposing the force field into conservative and nonconservative components, which are represented by a Lagrangian neural network (LNN) and an unconstrained neural network, respectively, trained to minimize the force recovery error plus a constant λ times the magnitude of the predicted nonconservative force. We show that a phase transition occurs at λ=1, universally for arbitrary forces. We demonstrate that NNPhD successfully discovers new physics in toy numerical experiments, rediscovering friction (1493) from a damped double pendulum, Neptune from Uranus' orbit (1846), and gravitational waves (2017) from an inspiraling orbit. We also show how NNPhD coupled with an integrator outperforms both an LNN and an unconstrained neural network for predicting the future of a damped double pendulum.
Efficient prediction of the air quality response to emission changes is a prerequisite for an integrated assessment system in developing effective control policies. Yet, representing the nonlinear ...response of air quality to emission controls with accuracy remains a major barrier in air quality-related decision making. Here, we demonstrate a novel method that combines deep learning approaches with chemical indicators of pollutant formation to quickly estimate the coefficients of air quality response functions using ambient concentrations of 18 chemical indicators simulated with a comprehensive atmospheric chemical transport model (CTM). By requiring only two CTM simulations for model application, the new method significantly enhances the computational efficiency compared to existing methods that achieve lower accuracy despite requiring 20+ CTM simulations (the benchmark statistical model). Our results demonstrate the utility of deep learning approaches for capturing the nonlinearity of atmospheric chemistry and physics and the prospects of the new method to support effective policymaking in other environment systems.