检索结果-内蒙古大学图书馆

Adaptive Low-Rank Gradient Descent

学校读者我要写书评

暂无评论

Adaptive Low-Rank Gradient Descent

IEEE Conference on Decision and Control

作者： Ali Jadbabaie Anuran Makur Amirhossein Reisizadeh Laboratory for Information & Decision Systems Massachusetts Institute of Technology Cambridge MA USA Department of Computer Science School of Electrical & Computer Engineering Purdue University West Lafayette IN USA

Low-rank structures have been observed in several recent empirical studies in many machine and deep learning problems, where the loss function demonstrates significant variation only in a lower dimensional subspace. While traditional gradient-based optimization algorithms are computationally costly for high-dimensional parameter spaces, such low-rank structures provide an opportunity to mitigate this cost. In this paper, we aim to leverage low-rank structures to alleviate the computational cost of first-order methods and study Adaptive Low-Rank Gradient Descent (AdaLRGD). The main idea of this method is to begin the optimization procedure in a very small subspace and gradually and adaptively augment it by including more directions. We show that for smooth and strongly convex objectives and any target accuracy $\epsilon$ , AdaLRGD's complexity is $\mathcal{O}(r\ln(r/\epsilon))$ for some rank $r$ no more than dimension $d$ . This significantly improves upon gradient descent's complexity of $\mathcal{O}(d\ln(1/\epsilon))$ when $r\ll d$ . We also propose a practical implementation of AdaLRGD and demonstrate its ability to leverage existing low-rank structures in data.

关键词：

Bounding Box-based Multi-objective Bayesian Optimization of Risk Measures under Input Uncertainty

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Inatsu, Yu Takeno, Shion Hanada, Hiroyuki Iwata, Kazuki Takeuchi, Ichiro Department of Computer Science Nagoya Institute of Technology Japan RIKEN Center for Advanced Intelligence Project Japan Department of Mechanical Systems Engineering Nagoya University Japan

In this study, we propose a novel multi-objective Bayesian optimization (MOBO) method to efficiently identify the Pareto front (PF) defined by risk measures for black-box functions under the presence of input uncertainty (IU). Existing BO methods for Pareto optimization in the presence of IU are risk-specific or without theoretical guarantees, whereas our proposed method addresses general risk measures and has theoretical guarantees. The basic idea of the proposed method is to assume a Gaussian process (GP) model for the black-box function and to construct high-probability bounding boxes for the risk measures using the GP model. Furthermore, in order to reduce the uncertainty of non-dominated bounding boxes, we propose a method of selecting the next evaluation point using a maximin distance defined by the maximum value of a quasi distance based on bounding boxes. As theoretical analysis, we prove that the algorithm can return an arbitrary-accurate solution in a finite number of iterations with high probability, for various risk measures such as Bayes risk, worst-case risk, and value-at-risk. We also give a theoretical analysis that takes into account approximation errors because there exist non-negligible approximation errors (e.g., finite approximation of PFs and sampling-based approximation of bounding boxes) in practice. We confirm that the proposed method outperforms compared with existing methods not only in the setting with IU but also in the setting of ordinary MOBO through numerical experiments. Copyright © 2023, The Authors. All rights reserved.

关键词： Numerical methods

3D polarimetry of laser induced speckle fields for phase detection thyroid gland polycrystalline structure and traumatic necrosis of human internal organs

学校读者我要写书评

暂无评论

3D polarimetry of laser induced speckle fields for phase det...

Photonics Applications in Astronomy, Communications, Industry, and High Energy Physics Experiments 2024

作者： Ushenko, Olexander Bilookyi, Olexander Ushenko, Yuriy Dubolazov, Alexander Soltys, Irina Olar, Olexander Mikirin, Ivan Skliarchuk, Valeriy Salega, Olexander Karas, Oleksandr Rakhimbayeva, Gulbarshin Rogovyi, Yuriy Kozan, Nataliia Zheng, Jun Alimbayeva, Zhadyra Omiotek, Zbigniew Taizhou Institute of Zhejiang University Taizhou China Optics and Publishing Department Chernivtsi National University Chernivtsi Ukraine Department of Surgery Bucovinian State Medical University Chernivtsi Ukraine Computer Science Department Chernivtsi National University Chernivtsi Ukraine Biomedical Engineering and Optic-Electronic Systems Department Vinnitsia National Technical University Vinnytsia Ukraine Department of Information Communication Technologies Kazakh National Medical University named after S.D. Asfendiyarova Almaty Kazakhstan Department of Pathological Physiology Bucovinian State Medical University Chernivtsi Ukraine Department of Forensic Medicine Medical and Pharmaceutical Law State Medical Academy Ivano-Frankivsk Ukraine Kazakh National Women's Teacher Training University Almaty Kazakhstan Faculty of Electrical Engineering and Computer Science Lublin University of Technology Lublin Poland

ISBN: (数字)9781510685796

ISBN: (纸本)9781510685789

A short theory of the processes of formation of the laser speckle fields polarization structure of biological tissues with optically anisotropic architectonics is presented. A method of polarization interference mapping of speckle fields with layer-by-layer phase scanning of holographically reconstructed distributions of complex amplitudes of biological preparations of various morphological structures and physiological states has been proposed and experimentally tested - biopsies of the thyroid gland and blood films of rats with different severity of sepsis. Layer-by-layer maps of polarization ellipticity of native histological sections of thyroid biopsies from donors and sick patients were studied. As part of the statistical analysis of phase coordinate distributions of polarization ellipticity, objective markers for the differential diagnosis of thyroid pathology were found - nodular goiter, autoimmune thyroiditis and papillary cancer. Very good (~90%) and excellent (≥90%) accuracy of differential diagnosis was achieved. Statistical markers for temporal monitoring of septic changes in polarization azimuth maps of polycrystalline blood films of rats were found. An example of further research using laser-induced autofluorescence polarimetry methods is presented. © 2024 SPIE.

关键词： Optical anisotropy

RoadFormer: Duplex Transformer for RGB-Normal Semantic Road Scene Parsing

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Li, Jiahang Zhang, Yikang Yun, Peng Zhou, Guangliang Chen, Qijun Fan, Rui The College of Electronics & Information Engineering Shanghai Research Institute for Intelligent Autonomous Systems The State Key Laboratory of Intelligent Autonomous Systems Frontiers Science Center for Intelligent Autonomous Systems Tongji University Shanghai201804 China The Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong

The recent advancements in deep convolutional neural networks have shown significant promise in the domain of road scene parsing. Nevertheless, the existing works focus primarily on freespace detection, with little attention given to hazardous road defects that could compromise both driving safety and comfort. In this article, we introduce RoadFormer, a novel Transformer-based data-fusion network developed for road scene parsing. RoadFormer utilizes a duplex encoder architecture to extract heterogeneous features from both RGB images and surface normal information. The encoded features are subsequently fed into a novel heterogeneous feature synergy block for effective feature fusion and recalibration. The pixel decoder then learns multi-scale long-range dependencies from the fused and recalibrated heterogeneous features, which are subsequently processed by a Transformer decoder to produce the final semantic prediction. Additionally, we release SYN-UDTIRI, the first large-scale road scene parsing dataset that contains over 10,407 RGB images, dense depth images, and the corresponding pixel-level annotations for both freespace and road defects of different shapes and sizes. Extensive experimental evaluations conducted on our SYN-UDTIRI dataset, as well as on three public datasets, including KITTI road, CityScapes, and ORFD, demonstrate that RoadFormer outperforms all other state-of-the-art networks for road scene parsing. Specifically, RoadFormer ranks first on the KITTI road benchmark. Our source code, created dataset, and demo video are publicly available at ***/RoadFormer. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantic Segmentation

Distributed Online Bandit Nonconvex Optimization with One-Point Residual Feedback via Dynamic Regret

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Hua, Youqing Liu, Shuai Hong, Yiguang Johansson, Karl Henrik Wang, Guangchen School of Control Science and Engineering Shandong University Jinan China Nanyang Technological University Singapore Department of Control Science and Engineering Shanghai Research Institute for Intelligent Autonomous Systems Tongji University Shanghai China School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden

This paper considers the distributed online bandit optimization problem with nonconvex loss functions over a time-varying digraph. This problem can be viewed as a repeated game between a group of online players and an adversary. At each round, each player selects a decision from the constraint set, and then the adversary assigns an arbitrary, possibly nonconvex, loss function to this player. Only the loss value at the current round, rather than the entire loss function or any other information (e.g. gradient), is privately revealed to the player. Players aim to minimize a sequence of global loss functions, which are the sum of local losses. We observe that traditional multi-point bandit algorithms are unsuitable for online optimization, where the data for the loss function are not all a priori, while the one-point bandit algorithms suffer from poor regret guarantees. To address these issues, we propose a novel one-point residual feedback distributed online algorithm. This algorithm estimates the gradient using residuals from two points, effectively reducing the regret bound while maintaining O(1) sampling complexity per iteration. We employ a rigorous metric, dynamic regret, to evaluate the algorithm's performance. By appropriately selecting the step size and smoothing parameters, we demonstrate that the expected dynamic regret of our algorithm is comparable to existing algorithms that use two-point feedback, provided the deviation in the objective function sequence and the path length of the minimization grows sublinearly. Finally, we validate the effectiveness of the proposed algorithm through numerical simulations. Copyright © 2024, The Authors. All rights reserved.

关键词： Optimization algorithms

Joint Hybrid Beamforming and RIS Phase Shift Design for RIS-Enabled Mmwave ISAC System

学校读者我要写书评

暂无评论

IEEE Transactions on Vehicular Technology 2025年

作者： Wang, Lu Abanto-Leon, Luis F. Asadi, Arash Ruhr University Bochum Faculty of Electrical Engineering and Information Technology Bochum Germany Technical University of Darmstadt Department of Computer Science Darmstadt64289 Germany TU Delft Embedded Systems Group DelftCD 2628 Netherlands

Empowering cellular networks with augmented sensing capabilities is a key research area in sixth generation (6 G) communication systems. Recently, we have witnessed a plethora of efforts to devise solutions that integrate sensing capabilities into communication systems, i.e., integrated sensing and communication (ISAC), especially at millimeter-wave (mmWave) frequencies with large bandwidths. Despite the challenges posed by severe path loss and blockage at mmWave bands, this work incorporates reconfigurable intelligent surfaces (RISs) into ISAC systems to enhance both sensing and communication. To comply with the waveform utilized in current cellular systems, this paper studies mmWave orthogonal frequency-division multiplexing (OFDM) ISAC systems in the presence of RISs. Specifically, we jointly design the hybrid beamforming and RIS phase shifts to guarantee the sensing functionalities via minimizing the beampattern mean squared error at RIS, subject to signal-to-interference-plus-noise (SINR) and power constraints. The non-convexity of the investigated problem poses a challenge which we address by proposing a solution based on the penalty method and manifold-based alternating direction method of multipliers (ADMM). Simulation results demonstrate that both sensing and communication capabilities improve when the RIS is adequately designed. In addition, we discuss the tradeoff between sensing and communication. © 2025 IEEE.

关键词： Mean square error

MERGING MULTIPLE INPUT DESCRIPTORS AND SUPERVISORS IN A DEEP NEURAL NETWORK FOR TRACTOGRAM FILTERING

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Jörgens, Daniel Jodoin, Pierre-Marc Descoteaux, Maxime Moreno, Rodrigo Department of Biomedical Engineering and Health Systems KTH Royal Institute of Technology Stockholm Sweden Department of Computer Science Université de Sherbrooke SherbrookeQC Canada

One of the main issues of the current tractography methods is their high false-positive rate. Tractogram filtering is an option to remove false-positive streamlines from tractography data in a post-processing step. In this paper, we train a deep neural network for filtering tractography data in which every streamline of a tractogram is classified as plausible, implausible, or inconclusive. For this, we use four different tractogram filtering strategies as supervisors: TractQuerier, RecobundlesX, TractSeg, and an anatomy-inspired filter. Their outputs are combined to obtain the classification labels for the streamlines. We assessed the importance of different types of information along the streamlines for performing this classification task, including the coordinates of the streamlines, diffusion data, landmarks, T1-weighted information, and a brain parcellation. We found that the streamline coordinates are the most relevant followed by the diffusion data in this particular classification task. © 2023, CC BY.

关键词： Deep neural networks

SSVEPPoolformer: An Improved Poolformer Model With the Adaptive Denoising Algorithm for SSVEP-EEG Signal Classification

学校读者我要写书评

暂无评论

IEEE Transactions on Consumer Electronics 2025年

作者： Li, Chunquan Liao, Zhiyuan Cheng, Yuxin Wang, Zitao Wu, Junyun Liu, Ruijun Liu, Peter X. Nanchang University School of Information Engineering Nanchang330031 China Nanchang University School of Mathematics and Computer Science Nanchang330031 China Beihang University School of Software Beijing100191 China Carleton University School of Department of Systems and Computer Engineering OttawaK1S 5B6 Canada

Most EEG classification algorithms based on steady-state visual evoked potentials (SSVEP-EEG) require filtering for denoising. However, manually set thresholds may inadvertently remove useful information, leading to a loss of significant signal features. Additionally, most deep learning-based SSVEP-EEG classification models have limited global feature extraction capabilities, and the self-attention mechanism in Transformers increases computational costs. To address these challenges, this paper proposes a novel SSVEP-EEG classification algorithm, SSVEPPoolformer. SSVEPPoolformer integrates an adaptive denoising algorithm with an improved Poolformer algorithm, enhancing both denoising performance and classification accuracy. The adaptive denoising algorithm dynamically adjusts the threshold using a compensation and adaptive adjustment mechanism, effectively filtering noise while retaining critical signal features. The improved Poolformer algorithm replaces the self-attention mechanism with an average pooling operation, reducing computational costs while maintaining performance. It also uses adaptive average pooling to integrate cross-channel feature information and extract global fine-grained features, improving global feature extraction. The SSVEPPoolformer model's efficacy was validated on two public datasets. Experimental results demonstrate that compared with other state-of-the-art methods, SSVEPPoolformer has higher classification accuracy and Information Transfer Rate (ITR) in both intra-class and inter-class recognition scenarios, and has lower computational cost. © 1975-2011 IEEE.

关键词： Electroencephalography

A Comparative Study of Implementing Intelligent Internet of Things for Creating Better Surveillance and Security in Developing Nations 2

学校读者我要写书评

暂无评论

A Comparative Study of Implementing Intelligent Internet of ...

2nd International Conference on Advance Computing and Innovative Technologies in engineering, ICACITE 2022

作者： Ganai, Prince Tehseen Nirmal, Ekanath Sitaram Kaushik, Manish Buddhi, Dharam Alam, Tanweer Rafi, Shaik Mohammad Shri Jagdishprasad Jhabarmal Tibrewala University Department of Information Technology Rajasthan India Arts Commerce and Science College Savitribai Phule Pune University Department of Political Science Pune India S. S. Jain Subodh P. G. College Master of Computer Applications Jaipur India Uttaranchal University Uit Uttarakhand Dehradun India Islamic University of Madinah Faculty of Computer and Information Systems Madinah Saudi Arabia Sri Mittapalli College of Engineering Department of Computer Science and Engineering Andhrapradesh Guntur India

ISBN: (纸本)9781665437899

In current history, rapid digitization has opened up new technical possibilities, which have already begun to alter the major safety and security sectors and society in general. The digital revolution opened up new opportunities for progress and more effective use of scarce resources, technologies, and operations in several sectors of the safety measurements. The Internet of Things (IoT) reflects the growth of mobile phones, houses, and integrated technologies. Because the items surrounding will have a greater understanding of our interests, ambitions, and requirements, such a development will aid in the creation of a smart environment for humans. Since IoT technologies grow more common, security challenges in IoT have gotten a lot of attention from academic and industrial. IoT systems, in comparison to traditional computing environments, have greater inherent problems and, as a result, may have increased security procedures. The existing IoT design, on the other hand, does not adequately handle the heightened security statutory responsibilities by those weaknesses. Mixed methods are used for this paper to collect statistical as well as theory-based information from different sources. Primary quantitative and secondary qualitative methods are used to collect various information. © 2022 IEEE.

关键词： Internet of things