Benefiting from huge bandwidth resources, millimeter-wave (mmWave) communications provide one of the most promising technologies for the fifth-generation wireless networks. To compensate for high pathloss of mmWave signals, large antenna arrays are equipped at base stations and user equipment to establish directional beamforming, where beam management is adopted to acquire and track the optimal beam pair with the maximum received power. Naturally, narrow beams are expected to achieve larger beamforming gain, whereas it could impose enormous training overhead and high sensitivity to blockages. Fortunately, the amazing success of deep learning (DL) has stimulated increasing interest in applying it to address those issues. In this article, we first elaborate the motivations of applying DL in beam management. Then, the current state-of-the-arts are reviewed, where their research routes and key features are discussed. Finally, challenges and future opportunities are summarized, highlighting DL design insights and novel beam management mechanisms. We hope this article can stimulate more striking ideas and exciting contributions for DL assisted beam management.
相關內容
The development of large quantum computers will have dire consequences for cryptography. Most of the symmetric and asymmetric cryptographic algorithms are vulnerable to quantum algorithms. Grover's search algorithm gives a square root time boost for the searching of the key in symmetric schemes like AES and 3DES. The security of asymmetric algorithms like RSA, Diffie Hellman, and ECC is based on the mathematical hardness of prime factorization and discrete logarithm. The best classical algorithms available take exponential time. Shor's factoring algorithm can solve the problems in polynomial time. Major breakthroughs in quantum computing will render all the present-day widely used asymmetric cryptosystems insecure. This paper analyzes the vulnerability of the classical cryptosystems in the context of quantum computers discusses various post-quantum cryptosystem families, discusses the status of the NIST post-quantum cryptography standardization process, and finally provides a couple of future research directions in this field.
Future wireless services must be focused on improving the quality of life by enabling various applications, such as extended reality, brain-computer interaction, and healthcare. These applications have diverse performance requirements (e.g., user-defined quality of experience metrics, latency, and reliability) that are challenging to be fulfilled by existing wireless systems. To meet the diverse requirements of the emerging applications, the concept of a digital twin has been recently proposed. A digital twin uses a virtual representation along with security-related technologies (e.g., blockchain), communication technologies (e.g., 6G), computing technologies (e.g., edge computing), and machine learning, so as to enable the smart applications. In this tutorial, we present a comprehensive overview on digital twins for wireless systems. First, we present an overview of fundamental concepts (i.e., design aspects, high-level architecture, and frameworks) of digital twin of wireless systems. Second, a comprehensive taxonomy is devised for both different aspects. These aspects are twins for wireless and wireless for twins. For the twins for wireless aspect, we consider parameters, such as twin objects design, prototyping, deployment trends, physical devices design, interface design, incentive mechanism, twins isolation, and decoupling. On the other hand, for wireless for twins, parameters such as, twin objects access aspects, security and privacy, and air interface design are considered. Finally, open research challenges and opportunities are presented along with causes and possible solutions.
Memory disaggregation addresses memory imbalance in a cluster by decoupling CPU and memory allocations of applications while also increasing the effective memory capacity for (memory-intensive) applications beyond the local memory limit imposed by traditional fixed-capacity servers. As the network speeds in the tightly-knit environments like modern datacenters inch closer to the DRAM speeds, there has been a recent proliferation of work in this space ranging from software solutions that pool memory of traditional servers for the shared use of the cluster to systems targeting the memory disaggregation in the hardware. In this report, we look at some of these recent memory disaggregation systems and study the important factors that guide their design, such as the interface through which the memory is exposed to the application, their runtime design and relevant optimizations to retain the near-native application performance, various approaches they employ in managing cluster memory to maximize utilization, etc. and we analyze the associated trade-offs. We conclude with a discussion on some open questions and potential future directions that can render disaggregation more amenable for adoption.
AI in finance broadly refers to the applications of AI techniques in financial businesses. This area has been lasting for decades with both classic and modern AI techniques applied to increasingly broader areas of finance, economy and society. In contrast to either discussing the problems, aspects and opportunities of finance that have benefited from specific AI techniques and in particular some new-generation AI and data science (AIDS) areas or reviewing the progress of applying specific techniques to resolving certain financial problems, this review offers a comprehensive and dense roadmap of the overwhelming challenges, techniques and opportunities of AI research in finance over the past decades. The landscapes and challenges of financial businesses and data are firstly outlined, followed by a comprehensive categorization and a dense overview of the decades of AI research in finance. We then structure and illustrate the data-driven analytics and learning of financial businesses and data. The comparison, criticism and discussion of classic vs. modern AI techniques for finance are followed. Lastly, open issues and opportunities address future AI-empowered finance and finance-motivated AI research.
Knowledge base question answering (KBQA) aims to answer a question over a knowledge base (KB). Recently, a large number of studies focus on semantically or syntactically complicated questions. In this paper, we elaborately summarize the typical challenges and solutions for complex KBQA. We begin with introducing the background about the KBQA task. Next, we present the two mainstream categories of methods for complex KBQA, namely semantic parsing-based (SP-based) methods and information retrieval-based (IR-based) methods. We then review the advanced methods comprehensively from the perspective of the two categories. Specifically, we explicate their solutions to the typical challenges. Finally, we conclude and discuss some promising directions for future research.
Federated Learning (FL) is a concept first introduced by Google in 2016, in which multiple devices collaboratively learn a machine learning model without sharing their private data under the supervision of a central server. This offers ample opportunities in critical domains such as healthcare, finance etc, where it is risky to share private user information to other organisations or devices. While FL appears to be a promising Machine Learning (ML) technique to keep the local data private, it is also vulnerable to attacks like other ML models. Given the growing interest in the FL domain, this report discusses the opportunities and challenges in federated learning.
As we seek to deploy machine learning models beyond virtual and controlled domains, it is critical to analyze not only the accuracy or the fact that it works most of the time, but if such a model is truly robust and reliable. This paper studies strategies to implement adversary robustly trained algorithms towards guaranteeing safety in machine learning algorithms. We provide a taxonomy to classify adversarial attacks and defenses, formulate the Robust Optimization problem in a min-max setting and divide it into 3 subcategories, namely: Adversarial (re)Training, Regularization Approach, and Certified Defenses. We survey the most recent and important results in adversarial example generation, defense mechanisms with adversarial (re)Training as their main defense against perturbations. We also survey mothods that add regularization terms that change the behavior of the gradient, making it harder for attackers to achieve their objective. Alternatively, we've surveyed methods which formally derive certificates of robustness by exactly solving the optimization problem or by approximations using upper or lower bounds. In addition, we discuss the challenges faced by most of the recent algorithms presenting future research perspectives.
Over the past few years, we have seen fundamental breakthroughs in core problems in machine learning, largely driven by advances in deep neural networks. At the same time, the amount of data collected in a wide array of scientific domains is dramatically increasing in both size and complexity. Taken together, this suggests many exciting opportunities for deep learning applications in scientific settings. But a significant challenge to this is simply knowing where to start. The sheer breadth and diversity of different deep learning techniques makes it difficult to determine what scientific problems might be most amenable to these methods, or which specific combination of methods might offer the most promising first approach. In this survey, we focus on addressing this central issue, providing an overview of many widely used deep learning models, spanning visual, sequential and graph structured data, associated tasks and different training methods, along with techniques to use deep learning with less data and better interpret these complex models --- two central considerations for many scientific use cases. We also include overviews of the full design process, implementation tips, and links to a plethora of tutorials, research summaries and open-sourced deep learning pipelines and pretrained models, developed by the community. We hope that this survey will help accelerate the use of deep learning across different scientific domains.
In the last years, Artificial Intelligence (AI) has achieved a notable momentum that may deliver the best of expectations over many application sectors across the field. For this to occur, the entire community stands in front of the barrier of explainability, an inherent problem of AI techniques brought by sub-symbolism (e.g. ensembles or Deep Neural Networks) that were not present in the last hype of AI. Paradigms underlying this problem fall within the so-called eXplainable AI (XAI) field, which is acknowledged as a crucial feature for the practical deployment of AI models. This overview examines the existing literature in the field of XAI, including a prospect toward what is yet to be reached. We summarize previous efforts to define explainability in Machine Learning, establishing a novel definition that covers prior conceptual propositions with a major focus on the audience for which explainability is sought. We then propose and discuss about a taxonomy of recent contributions related to the explainability of different Machine Learning models, including those aimed at Deep Learning methods for which a second taxonomy is built. This literature analysis serves as the background for a series of challenges faced by XAI, such as the crossroads between data fusion and explainability. Our prospects lead toward the concept of Responsible Artificial Intelligence, namely, a methodology for the large-scale implementation of AI methods in real organizations with fairness, model explainability and accountability at its core. Our ultimate goal is to provide newcomers to XAI with a reference material in order to stimulate future research advances, but also to encourage experts and professionals from other disciplines to embrace the benefits of AI in their activity sectors, without any prior bias for its lack of interpretability.
Reinforcement learning (RL) algorithms have been around for decades and been employed to solve various sequential decision-making problems. These algorithms however have faced great challenges when dealing with high-dimensional environments. The recent development of deep learning has enabled RL methods to drive optimal policies for sophisticated and capable agents, which can perform efficiently in these challenging environments. This paper addresses an important aspect of deep RL related to situations that demand multiple agents to communicate and cooperate to solve complex tasks. A survey of different approaches to problems related to multi-agent deep RL (MADRL) is presented, including non-stationarity, partial observability, continuous state and action spaces, multi-agent training schemes, multi-agent transfer learning. The merits and demerits of the reviewed methods will be analyzed and discussed, with their corresponding applications explored. It is envisaged that this review provides insights about various MADRL methods and can lead to future development of more robust and highly useful multi-agent learning methods for solving real-world problems.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191