The presence of long-range interactions is crucial in distinguishing between abstract complex networks and wave *** photonics,because electromagnetic interactions between optical elements generally decay rapidly with ...
详细信息
The presence of long-range interactions is crucial in distinguishing between abstract complex networks and wave *** photonics,because electromagnetic interactions between optical elements generally decay rapidly with spatial distance,most wave phenomena are modeled with neighboring interactions,which account for only a small part of conceptually possible ***,we explore the impact of substantial long-range interactions in topological *** demonstrate that a crystalline structure,characterized by long-range interactions in the absence of neighboring ones,can be interpreted as an overlapped *** overlap model facilitates the realization of higher values of topological invariants while maintaining bandgap width in photonic topological *** breaking of topology-bandgap tradeoff enables topologically protected multichannel signal processing with broad *** practically accessible system parameters,the result paves the way to the extension of topological physics to network science.
This study introduces a data-driven approach for state and output feedback control addressing the constrained output regulation problem in unknown linear discrete-time systems. Our method ensures effective tracking pe...
详细信息
This study introduces a data-driven approach for state and output feedback control addressing the constrained output regulation problem in unknown linear discrete-time systems. Our method ensures effective tracking performance while satisfying the state and input constraints, even when system matrices are not available. We first establish a sufficient condition necessary for the existence of a solution pair to the regulator equation and propose a data-based approach to obtain the feedforward and feedback control gains for state feedback control using linear programming. Furthermore, we design a refined Luenberger observer to accurately estimate the system state, while keeping the estimation error within a predefined set. By combining output regulation theory, we develop an output feedback control strategy. The stability of the closed-loop system is rigorously proved to be asymptotically stable by further leveraging the concept of λ-contractive sets.
We have witnessed the emergence of superhuman intelligence thanks to the fast development of large language models(LLMs) and multimodal language models. As the application of such superhuman models becomes increasingl...
详细信息
We have witnessed the emergence of superhuman intelligence thanks to the fast development of large language models(LLMs) and multimodal language models. As the application of such superhuman models becomes increasingly popular, a critical question arises: how can we ensure they still remain safe, reliable, and aligned well with human values encompassing moral values, Schwartz's Values, ethics, and many more? In this position paper, we discuss the concept of superalignment from a learning perspective to answer this question by outlining the learning paradigm shift from large-scale pretraining and supervised fine-tuning, to alignment training. We define superalignment as designing effective and efficient alignment algorithms to learn from noisy-labeled data(point-wise samples or pair-wise preference data) in a scalable way when the task is very complex for human experts to annotate and when the model is stronger than human experts. We highlight some key research problems in superalignment, namely, weak-to-strong generalization, scalable oversight, and evaluation. We then present a conceptual framework for superalignment, which comprises three modules: an attacker which generates the adversary queries trying to expose the weaknesses of a learner model, a learner which refines itself by learning from scalable feedbacks generated by a critic model with minimal human experts, and a critic which generates critics or explanations for a given query-response pair, with a target of improving the learner by criticizing. We discuss some important research problems in each component of this framework and highlight some interesting research ideas that are closely related to our proposed framework, for instance, self-alignment, self-play, self-refinement, and more. Last, we highlight some future research directions for superalignment, including the identification of new emergent risks and multi-dimensional alignment.
Eye health has become a global health concern and attracted broad *** the years,researchers have proposed many state-of-the-art convolutional neural networks(CNNs)to assist ophthalmologists in diagnosing ocular diseas...
详细信息
Eye health has become a global health concern and attracted broad *** the years,researchers have proposed many state-of-the-art convolutional neural networks(CNNs)to assist ophthalmologists in diagnosing ocular diseases efficiently and ***,most existing methods were dedicated to constructing sophisticated CNNs,inevitably ignoring the trade-off between performance and model *** alleviate this paradox,this paper proposes a lightweight yet efficient network architecture,mixeddecomposed convolutional network(MDNet),to recognise ocular *** MDNet,we introduce a novel mixed-decomposed depthwise convolution method,which takes advantage of depthwise convolution and depthwise dilated convolution operations to capture low-resolution and high-resolution patterns by using fewer computations and fewer *** conduct extensive experiments on the clinical anterior segment optical coherence tomography(AS-OCT),LAG,University of California San Diego,and CIFAR-100 *** results show our MDNet achieves a better trade-off between the performance and model complexity than efficient CNNs including MobileNets and ***,our MDNet outperforms MobileNets by 2.5%of accuracy by using 22%fewer parameters and 30%fewer computations on the AS-OCT dataset.
Graph structure expression plays a vital role in distinguishing various graphs. In this work, we propose a structure-sensitive graph dictionary embedding (SS-GDE) framework to transform input graphs into the embedding...
详细信息
This paper presents a review on methods for class-imbalanced learning with the Support Vector Machine (SVM) and its variants. We first explain the structure of SVM and its variants and discuss their inefficiency in le...
详细信息
作者:
Liu, XinWen, ShuhuanLiu, HuapingRichard Yu, F.Yanshan University
Engineering Research Center of the Ministry of Education for Intelligent Control System and Intelligent Equipment Key Laboratory of Intelligent Rehabilitation and Neuroregulation in Hebei Province Department of Key Laboratory of Industrial Computer Control Engineering of Hebei Province Qinhuangdao066004 China Tsinghua University
Department of Computer Science and Technology Beijing100084 China Shenzhen University
College of Computer Science and Software Engineering Shenzhen518060 China Carleton University
School of Information Technology Department of Systems and Computer Engineering OttawaONK1S 5B6 Canada
Traditional visual-inertial Simultaneous Localization and Mapping (SLAM) systems predominantly rely on feature point matching from a single robot to realize the robot pose estimation and environment map construction. ...
详细信息
The proliferation of Internet of Things (IoT) technologies and ubiquitous connectivity has led to uncrewed aerial vehicles (UAVs) playing key role as edge servers, revolutionizing the wireless communications landscape...
详细信息
Learning network dynamics from the empirical structure and spatio-temporal observation data is crucial to revealing the interaction mechanisms of complex networks in a wide range of domains. However,most existing meth...
详细信息
Learning network dynamics from the empirical structure and spatio-temporal observation data is crucial to revealing the interaction mechanisms of complex networks in a wide range of domains. However,most existing methods only aim at learning network dynamic behaviors generated by a specific ordinary differential equation instance, resulting in ineffectiveness for new ones, and generally require dense *** observed data, especially from network emerging dynamics, are usually difficult to obtain, which brings trouble to model learning. Therefore, learning accurate network dynamics with sparse, irregularly-sampled,partial, and noisy observations remains a fundamental challenge. We introduce a new concept of the stochastic skeleton and its neural implementation, i.e., neural ODE processes for network dynamics(NDP4ND), a new class of stochastic processes governed by stochastic data-adaptive network dynamics, to overcome the challenge and learn continuous network dynamics from scarce observations. Intensive experiments conducted on various network dynamics in ecological population evolution, phototaxis movement, brain activity, epidemic spreading, and real-world empirical systems, demonstrate that the proposed method has excellent data adaptability and computational efficiency, and can adapt to unseen network emerging dynamics, producing accurate interpolation and extrapolation with reducing the ratio of required observation data to only about 6% and improving the learning speed for new dynamics by three orders of magnitude.
Precise polyp segmentation is vital for the early diagnosis and prevention of colorectal cancer(CRC)in clinical ***,due to scale variation and blurry polyp boundaries,it is still a challenging task to achieve satisfac...
详细信息
Precise polyp segmentation is vital for the early diagnosis and prevention of colorectal cancer(CRC)in clinical ***,due to scale variation and blurry polyp boundaries,it is still a challenging task to achieve satisfactory segmentation performance with different scales and *** this study,we present a novel edge-aware feature aggregation network(EFA-Net)for polyp segmentation,which can fully make use of cross-level and multi-scale features to enhance the performance of polyp ***,we first present an edge-aware guidance module(EGM)to combine the low-level features with the high-level features to learn an edge-enhanced feature,which is incorporated into each decoder unit using a layer-by-layer ***,a scale-aware convolution module(SCM)is proposed to learn scale-aware features by using dilated convolutions with different ratios,in order to effectively deal with scale ***,a cross-level fusion module(CFM)is proposed to effectively integrate the cross-level features,which can exploit the local and global contextual ***,the outputs of CFMs are adaptively weighted by using the learned edge-aware feature,which are then used to produce multiple side-out segmentation *** results on five widely adopted colonoscopy datasets show that our EFA-Net outperforms state-of-the-art polyp segmentation methods in terms of generalization and *** implementation code and segmentation maps will be publicly at https://***/taozh2017/EFANet.
暂无评论