Showing papers on "Field (mathematics) published in 2021"

A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects.

Abstract: A convolutional neural network (CNN) is one of the most significant networks in the deep learning field. Since CNN made impressive achievements in many areas, including but not limited to computer vision and natural language processing, it attracted much attention from both industry and academia in the past few years. The existing reviews mainly focus on CNN's applications in different scenarios without considering CNN from a general perspective, and some novel ideas proposed recently are not covered. In this review, we aim to provide some novel ideas and prospects in this fast-growing field. Besides, not only 2-D convolution but also 1-D and multidimensional ones are involved. First, this review introduces the history of CNN. Second, we provide an overview of various convolutions. Third, some classic and advanced CNN models are introduced; especially those key points making them reach state-of-the-art results. Fourth, through experimental analysis, we draw some conclusions and provide several rules of thumb for functions and hyperparameter selection. Fifth, the applications of 1-D, 2-D, and multidimensional convolution are covered. Finally, some open issues and promising directions for CNN are discussed as guidelines for future work.

Deep Learning on Traffic Prediction: Methods, Analysis and Future Directions

Abstract: Traffic prediction plays an essential role in intelligent transportation system. Accurate traffic prediction can assist route planing, guide vehicle dispatching, and mitigate traffic congestion. This problem is challenging due to the complicated and dynamic spatio-temporal dependencies between different regions in the road network. Recently, a significant amount of research efforts have been devoted to this area, especially deep learning method, greatly advancing traffic prediction abilities. The purpose of this paper is to provide a comprehensive survey on deep learning-based approaches in traffic prediction from multiple perspectives. Specifically, we first summarize the existing traffic prediction methods, and give a taxonomy. Second, we list the state-of-the-art approaches in different traffic prediction applications. Third, we comprehensively collect and organize widely used public datasets in the existing literature to facilitate other researchers. Furthermore, we give an evaluation and analysis by conducting extensive experiments to compare the performance of different methods on a real-world public dataset. Finally, we discuss open challenges in this field.

Human Trajectory Forecasting in Crowds: A Deep Learning Perspective

Abstract: Since the past few decades, human trajectory forecasting has been a field of active research owing to its numerous real-world applications: evacuation situation analysis, deployment of intelligent transport systems, traffic operations, to name a few. In this work, we cast the problem of human trajectory forecasting as learning a representation of human social interactions. Early works handcrafted this representation based on domain knowledge. However, social interactions in crowded environments are not only diverse but often subtle. Recently, deep learning methods have outperformed their handcrafted counterparts, as they learn about human-human interactions in a more generic data-driven fashion. In this work, we present an in-depth analysis of existing deep learning-based methods for modelling social interactions. We propose two domain-knowledge inspired data-driven methods to effectively capture these social interactions. To objectively compare the performance of these interaction-based forecasting models, we develop a large scale interaction-centric benchmark TrajNet++, a significant yet missing component in the field of human trajectory forecasting. We propose novel performance metrics that evaluate the ability of a model to output socially acceptable trajectories. Experiments on TrajNet++ validate the need for our proposed metrics, and our method outperforms competitive baselines on both real-world and synthetic datasets.

A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications

Abstract: Generative adversarial networks (GANs) have recently become a hot research topic; however, they have been studied since 2014, and a large number of algorithms have been proposed. However, few comprehensive studies exist explaining the connections among different GANs variants and how they have evolved. In this paper, we attempt to provide a review of the various GANs methods from the perspectives of algorithms, theory, and applications. First, the motivations, mathematical representations, and structures of most GANs algorithms are introduced in detail and we compare their commonalities and differences. Second, theoretical issues related to GANs are investigated. Finally, typical applications of GANs in image processing and computer vision, natural language processing, music, speech and audio, medical field, and data science are discussed.

Double Parameters Fractal Sorting Matrix and Its Application in Image Encryption

Abstract: In the field of frontier research, information security has received a lot of interest, but in the field of information security algorithm, the introduction of decimals makes it impossible to bypass the topic of calculation accuracy. This article creatively proposes the definition and related proofs of double parameters fractal sorting matrix (DPFSM). As a new matrix classification with fractal properties, DPFSM contains self-similar structures in the ordering of both elements and sub-blocks in the matrix. These two self-similar structures are determined by two different parameters. To verify the theory, this paper presents a type of 2×2 DPFSM iterative generation method, as well as the theory, steps, and examples of the iteration. DPFSM is a space position transformation matrix, which has a better periodic law than a single parameter fractal sorting matrix (FSM). The proposal of DPFSM expands the fractal theory and solves the limitation of calculation accuracy on information security. The image encryption algorithm based on DPFSM is proposed, and the security analysis demonstrates the security. DPFSM has good application value in the field of information security.

New Generation Deep Learning for Video Object Detection: A Survey

Abstract: Video object detection, a basic task in the computer vision field, is rapidly evolving and widely used In recent years, deep learning methods have rapidly become widespread in the field of video object detection, achieving excellent results compared with those of traditional methods However, the presence of duplicate information and abundant spatiotemporal information in video data poses a serious challenge to video object detection Therefore, in recent years, many scholars have investigated deep learning detection algorithms in the context of video data and have achieved remarkable results Considering the wide range of applications, a comprehensive review of the research related to video object detection is both a necessary and challenging task This survey attempts to link and systematize the latest cutting-edge research on video object detection with the goal of classifying and analyzing video detection algorithms based on specific representative models The differences and connections between video object detection and similar tasks are systematically demonstrated, and the evaluation metrics and video detection performance of nearly 40 models on two data sets are presented Finally, the various applications and challenges facing video object detection are discussed

Recent Advances and Applications of Deep Learning Methods in Materials Science

Abstract: Deep learning (DL) is one of the fastest growing topics in materials data science, with rapidly emerging applications spanning atomistic, image-based, spectral, and textual data modalities. DL allows analysis of unstructured data and automated identification of features. Recent development of large materials databases has fueled the application of DL methods in atomistic prediction in particular. In contrast, advances in image and spectral data have largely leveraged synthetic data enabled by high quality forward models as well as by generative unsupervised DL methods. In this article, we present a high-level overview of deep-learning methods followed by a detailed discussion of recent developments of deep learning in atomistic simulation, materials imaging, spectral analysis, and natural language processing. For each modality we discuss applications involving both theoretical and experimental data, typical modeling approaches with their strengths and limitations, and relevant publicly available software and datasets. We conclude the review with a discussion of recent cross-cutting work related to uncertainty quantification in this field and a brief perspective on limitations, challenges, and potential growth areas for DL methods in materials science. The application of DL methods in materials science presents an exciting avenue for future materials discovery and design.

Modern Koopman Theory for Dynamical Systems.

Abstract: The field of dynamical systems is being transformed by the mathematical tools and algorithms emerging from modern computing and data science. First-principles derivations and asymptotic reductions are giving way to data-driven approaches that formulate models in operator theoretic or probabilistic frameworks. Koopman spectral theory has emerged as a dominant perspective over the past decade, in which nonlinear dynamics are represented in terms of an infinite-dimensional linear operator acting on the space of all possible measurement functions of the system. This linear representation of nonlinear dynamics has tremendous potential to enable the prediction, estimation, and control of nonlinear systems with standard textbook methods developed for linear systems. However, obtaining finite-dimensional coordinate systems and embeddings in which the dynamics appear approximately linear remains a central open challenge. The success of Koopman analysis is due primarily to three key factors: 1) there exists rigorous theory connecting it to classical geometric approaches for dynamical systems, 2) the approach is formulated in terms of measurements, making it ideal for leveraging big-data and machine learning techniques, and 3) simple, yet powerful numerical algorithms, such as the dynamic mode decomposition (DMD), have been developed and extended to reduce Koopman theory to practice in real-world applications. In this review, we provide an overview of modern Koopman operator theory, describing recent theoretical and algorithmic developments and highlighting these methods with a diverse range of applications. We also discuss key advances and challenges in the rapidly growing field of machine learning that are likely to drive future developments and significantly transform the theoretical landscape of dynamical systems.

Conformal blocks from celestial gluon amplitudes

Abstract: In celestial conformal field theory, gluons are represented by primary fields with dimensions ∆ = 1 + iλ, λ ∈ ℝ and spin J = ±1, in the adjoint representation of the gauge group. All two- and three-point correlation functions of these fields are zero as a consequence of four-dimensional kinematic constraints. Four-point correlation functions contain delta-function singularities enforcing planarity of four-particle scattering events. We relax these constraints by taking a shadow transform of one field and perform conformal block decomposition of the corresponding correlators. We compute the conformal block coefficients. When decomposed in channels that are “compatible” in two and four dimensions, such four-point correlators contain conformal blocks of primary fields with dimensions ∆ = 2 + M + iλ, where M ≥ 0 is an integer, with integer spin J = −M, −M + 2, …, M − 2, M. They appear in all gauge group representations obtained from a tensor product of two adjoint representations. When decomposed in incompatible channels, they also contain primary fields with continuous complex spin, but with positive integer dimensions.

A Survey on Evolutionary Neural Architecture Search.

Abstract: Deep neural networks (DNNs) have achieved great success in many applications. The architectures of DNNs play a crucial role in their performance, which is usually manually designed with rich expertise. However, such a design process is labor-intensive because of the trial-and-error process and also not easy to realize due to the rare expertise in practice. Neural architecture search (NAS) is a type of technology that can design the architectures automatically. Among different methods to realize NAS, the evolutionary computation (EC) methods have recently gained much attention and success. Unfortunately, there has not yet been a comprehensive summary of the EC-based NAS algorithms. This article reviews over 200 articles of most recent EC-based NAS methods in light of the core components, to systematically discuss their design principles and justifications on the design. Furthermore, current challenges and issues are also discussed to identify future research in this emerging field.

A Survey of Human-in-the-loop for Machine Learning.

Abstract: Human-in-the-loop aims to train an accurate prediction model with minimum cost by integrating human knowledge and experience. Humans can provide training data for machine learning applications and directly accomplish some tasks that are hard for computers in the pipeline with the help of machine-based approaches. In this paper, we survey existing works on human-in-the-loop from a data perspective and classify them into three categories with a progressive relationship: (1) the work of improving model performance from data processing, (2) the work of improving model performance through interventional model training, and (3) the design of the system independent human-in-the-loop. Using the above categorization, we summarize major approaches in the field, along with their technical strengths/ weaknesses, we have simple classification and discussion in natural language processing, computer vision, and others. Besides, we provide some open challenges and opportunities. This survey intends to provide a high-level summarization for human-in-the-loop and motivates interested readers to consider approaches for designing effective human-in-the-loop solutions.

Deep Neural Networks and Tabular Data: A Survey

Abstract: Heterogeneous tabular data are the most commonly used form of data and are essential for numerous critical and computationally demanding applications. On homogeneous data sets, deep neural networks have repeatedly shown excellent performance and have therefore been widely adopted. However, their application to modeling tabular data (inference or generation) remains highly challenging. This work provides an overview of state-of-the-art deep learning methods for tabular data. We start by categorizing them into three groups: data transformations, specialized architectures, and regularization models. We then provide a comprehensive overview of the main approaches in each group. A discussion of deep learning approaches for generating tabular data is complemented by strategies for explaining deep models on tabular data. Our primary contribution is to address the main research streams and existing methodologies in this area, while highlighting relevant challenges and open research questions. To the best of our knowledge, this is the first in-depth look at deep learning approaches for tabular data. This work can serve as a valuable starting point and guide for researchers and practitioners interested in deep learning with tabular data.

Reinforcement learning based recommender systems: A survey.

Abstract: Recommender systems (RSs) are becoming an inseparable part of our everyday lives. They help us find our favorite items to purchase, our friends on social networks, and our favorite movies to watch. Traditionally, the recommendation problem was considered as a simple classification or prediction problem; however, the sequential nature of the recommendation problem has been shown. Accordingly, it can be formulated as a Markov decision process (MDP) and reinforcement learning (RL) methods can be employed to solve it. In fact, recent advances in combining deep learning with traditional RL methods, i.e. deep reinforcement learning (DRL), has made it possible to apply RL to the recommendation problem with massive state and action spaces. In this paper, a survey on reinforcement learning based recommender systems (RLRSs) is presented. We first recognize the fact that algorithms developed for RLRSs can be generally classified into RL- and DRL-based methods. Then, we present these RL- and DRL-based methods in a classified manner based on the specific RL algorithm, e.g., Q-learning, SARSA, and REINFORCE, that is used to optimize the recommendation policy. Furthermore, some tables are presented that contain detailed information about the MDP formulation of these methods, as well as about their evaluation schemes. Finally, we discuss important aspects and challenges that can be addressed in the future.

Linear Diophantine fuzzy algebraic structures

Abstract: The main objective of this paper is to introduce some algebraic properties of finite linear Diophantine fuzzy subsets of group, ring and field. Relatedly, we define the concepts of linear Diophantine fuzzy subgroup and normal subgroup of a group, linear Diophantine fuzzy subring and ideal of a ring, and linear Diophantine fuzzy subfield of a field. We investigate their basic properties, relations and characterizations in detail. Furthermore, we establish the homomorphic images and preimages of the emerged linear Diophantine fuzzy algebraic structures. Finally, we describe linear Diophantine fuzzy code and investigate the relationships between this code and some linear Diophantine fuzzy algebraic structures.

A Survey of Brain-Inspired Intelligent Robots: Integration of Vision, Decision, Motion Control, and Musculoskeletal Systems.

Abstract: Current robotic studies are focused on the performance of specific tasks. However, such tasks cannot be generalized, and some special tasks, such as compliant and precise manipulation, fast and flexible response, and deep collaboration between humans and robots, cannot be realized. Brain-inspired intelligent robots imitate humans and animals, from inner mechanisms to external structures, through an integration of visual cognition, decision making, motion control, and musculoskeletal systems. This kind of robot is more likely to realize the functions that current robots cannot realize and become human friends. With the focus on the development of brain-inspired intelligent robots, this article reviews cutting-edge research in the areas of brain-inspired visual cognition, decision making, musculoskeletal robots, motion control, and their integration. It aims to provide greater insight into brain-inspired intelligent robots and attracts more attention to this field from the global research community.

A Conceptual Model and Taxonomy for Collaborative Augmented Reality.

Abstract: To support the nuances of collaborative work, many researchers have been exploring the field of Augmented Reality (AR),aiming to assist in co-located or remote scenarios. Solutions using AR allow taking advantage from seamless integration of virtualobjects and real-world objects, thus providing collaborators with a shared understanding or common ground environment. However,most of the research efforts, so far, have been devoted to experiment with technology and mature methods to support its design anddevelopment. Therefore, it is now time to understand were do we stand and how well can we address collaborative work with AR, tobetter characterize and evaluate the collaboration process. In this paper, we perform an analysis of the different dimensions that shouldbe taken into account when analysing the contributions of AR to the collaborative work effort. Then, we bring these dimensions forwardinto a conceptual framework and propose an extended human-centered taxonomy for the categorization of the main features of Collaborative AR. Our goal is to foster harmonization of perspectives for the field, which may help create a common ground forsystematization and discussion. We hope to influence and improve how research in this field is reported by providing a structured list ofthe defining characteristics. Finally, some examples of the use of the taxonomy are presented to show how it can serve to gatherinformation for characterizing AR-supported collaborative work, and illustrate its potential as the grounds to elicit further.

Solutions of Modular Bootstrap Constraints from Quantum Codes.

Abstract: Modular invariance imposes rigid constraints on the partition functions of two-dimensional conformal field theories (CFTs). Many fundamental results follow strictly from modular invariance and unitarity, giving rise to the numerical modular bootstrap program. Here we report on a way to relate a particular family of quantum error correcting codes to a family of ``code CFTs,'' which forms a subset of the space of Narain CFTs. This correspondence reduces modular invariance of the 2D CFT partition function to a few simple algebraic relations obeyed by a multivariate polynomial characterizing the corresponding code. Using this correspondence, we construct many explicit examples of physically distinct isospectral theories, as well as many examples of nonholomorphic functions, which satisfy all the basic properties of a 2D CFT partition function, yet are not associated with any known CFT.

Intelligent metaphotonics empowered by machine learning

Abstract: In the recent years, we observe a dramatic boost of research in photonics empowered by the concepts of machine learning and artificial intelligence. The corresponding photonic systems, to which this new methodology is applied, can range from traditional optical waveguides to nanoantennas and metasurfaces, and these novel approaches underpin the fundamental principles of light-matter interaction developed for a smart design of intelligent photonic devices. Concepts and approaches of artificial intelligence and machine learning penetrate rapidly into the fundamental physics of light, and they provide effective tools for the study of the field of metaphotonics driven by optically-induced electric and magnetic resonances. Here, we introduce this new field with its application to metaphotonics and also present a summary of the basic concepts of machine learning with some specific examples developed and demonstrated for metasystems and metasurfaces.

Introduction to theory of high-harmonic generation in solids: tutorial

Abstract: High-harmonic generation (HHG) in solids has emerged in recent years as a rapidly expanding and interdisciplinary field, attracting attention from both the condensed-matter and the atomic, molecular, and optics communities. It has exciting prospects for the engineering of new light sources and the probing of ultrafast carrier dynamics in solids, and the theoretical understanding of this process is of fundamental importance. This tutorial provides a hands-on introduction to the theoretical description of the strong-field laser-matter interactions in a condensed-phase system that give rise to HHG. We provide an overview ranging from a detailed description of different approaches to calculating the microscopic dynamics and how these are intricately connected to the description of the crystal structure, through the conceptual understanding of HHG in solids as supported by the semiclassical recollision model, and finally a brief description of how to calculate the macroscopic response. We also give a general introduction to the Berry phase, and we discuss important subtleties in the modelling of HHG, such as the choice of structure and laser gauges, and the construction of a smooth and periodic structure gauge for both nondegenerate and degenerate bands. The advantages and drawback of different structure and laser-gauge choices are discussed, both in terms of their ability to address specific questions and in terms of their numerical feasibility.

A Survey on Data Augmentation for Text Classification.

Abstract: Data augmentation, the artificial creation of training data for machine learning by transformations, is a widely studied research field across machine learning disciplines. While it is useful for increasing the generalization capabilities of a model, it can also address many other challenges and problems, from overcoming a limited amount of training data over regularizing the objective to limiting the amount data used to protect privacy. Based on a precise description of the goals and applications of data augmentation (C1) and a taxonomy for existing works (C2), this survey is concerned with data augmentation methods for textual classification and aims to achieve a concise and comprehensive overview for researchers and practitioners (C3). Derived from the taxonomy, we divided more than 100 methods into 12 different groupings and provide state-of-the-art references expounding which methods are highly promising (C4). Finally, research perspectives that may constitute a building block for future work are given (C5).

A Comprehensive Review of Computer-aided Whole-slide Image Analysis: from Datasets to Feature Extraction, Segmentation, Classification, and Detection Approaches.

Abstract: With the development of computer-aided diagnosis (CAD) and image scanning technology, Whole-slide Image (WSI) scanners are widely used in the field of pathological diagnosis. Therefore, WSI analysis has become the key to modern digital pathology. Since 2004, WSI has been used more and more in CAD. Since machine vision methods are usually based on semi-automatic or fully automatic computers, they are highly efficient and labor-saving. The combination of WSI and CAD technologies for segmentation, classification, and detection helps histopathologists obtain more stable and quantitative analysis results, save labor costs and improve diagnosis objectivity. This paper reviews the methods of WSI analysis based on machine learning. Firstly, the development status of WSI and CAD methods are introduced. Secondly, we discuss publicly available WSI datasets and evaluation metrics for segmentation, classification, and detection tasks. Then, the latest development of machine learning in WSI segmentation, classification, and detection are reviewed continuously. Finally, the existing methods are studied, the applicabilities of the analysis methods are analyzed, and the application prospects of the analysis methods in this field are forecasted.