检索结果-内蒙古大学图书馆

Distributed sparse SGD with majority voting

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Özfatura, Kerem Ozfatura, Emre Gündüz, Deniz Department of Computer Science Ozyegin University Istanbul Turkey Information Processing and Communications Lab Dept. of Electrical and Electronic Engineering Imperial College London London United Kingdom

Distributed learning, particularly variants of distributed stochastic gradient descent (DSGD), are widely employed to speed up training by leveraging computational resources of several workers. However, in practise, communication delay becomes a bottleneck due to the significant amount of information that needs to be exchanged between the workers and the parameter server. One of the most efficient strategies to mitigate the communication bottleneck is top-K sparsification. However, top-K sparsification requires additional communication load to represent the sparsity pattern, and the mismatch between the sparsity patterns of the workers prevents exploitation of efficient communication protocols. To address these issues, we introduce a novel majority voting based sparse communication strategy, in which the workers first seek a consensus on the structure of the sparse representation. This strategy provides a significant reduction in the communication load and allows using the same sparsity level in both communication directions. Through extensive simulations on the CIFAR-10 dataset, we show that it is possible to achieve up to ×4000 compression without any loss in the test accuracy. Copyright © 2020, The Authors. All rights reserved.

关键词： Gradient methods

Confidence-Regulated Generative Diffusion Models for Reliable AI Agent Migration in Vehicular Metaverses

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Kang, Yingkai Kang, Jiawen Wen, Jinbo Zhang, Tao Yang, Zhaohui Niyato, Dusit Zhang, Yan School of Automation Guangdong University of Technology Guangzhou510006 China College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing210016 China School of Cyberspace Science and Technology Beijing Jiaotong University Beijing100044 China College of Information Science and Electronic Engineering Zhejiang Provincial Key Lab of information processing communication and networking Zhejiang University Hangzhou310007 China College of Computing and Data Science Nanyang Technological University Singapore Department of Informatics University of Oslo the Simula Research Laboratory Norway

Vehicular metaverses are an emerging paradigm that merges intelligent transportation systems with virtual spaces, leveraging advanced digital twin and Artificial Intelligence (AI) technologies to seamlessly integrate vehicles, users, and digital environments. In this paradigm, vehicular AI agents are endowed with environment perception, decision-making, and action execution capabilities, enabling real-time processing and analysis of multi-modal data to provide users with customized interactive services. Since vehicular AI agents require substantial resources for real-time decision-making, given vehicle mobility and network dynamics conditions, the AI agents are deployed in RoadSide Units (RSUs) with sufficient resources and dynamically migrated among them. However, AI agent migration requires frequent data exchanges, which may expose vehicular metaverses to potential cyber attacks. To this end, we propose a reliable vehicular AI agent migration framework, achieving reliable dynamic migration and efficient resource scheduling through cooperation between vehicles and RSUs. Additionally, we design a trust evaluation model based on the theory of planned behavior to dynamically quantify the reputation of RSUs, thereby better accommodating the personalized trust preferences of users. We then model the vehicular AI agent migration process as a partially observable markov decision process and develop a Confidence-regulated Generative Diffusion Model (CGDM) to efficiently generate AI agent migration decisions. Numerical results demonstrate that the CGDM algorithm significantly outperforms baseline methods in reducing system latency and enhancing robustness against cyber attacks. Copyright © 2025, The Authors. All rights reserved.

关键词： Markov processes

A Review of Artificial Fish Swarm Algorithms: Recent Advances and Applications

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Pourpanah, Farhad Wang, Ran Lim, Chee Peng Wang, Xi-Zhao Yazdani, Danial College of Mathematics and Statistics Guangdong Key Lab. of Intelligent Information Processing Shenzhen University China Department of Electrical and Computer Engineering University of Windsor Canada College of Mathematics and Statistics Shenzhen Key Lab. of Advanced Machine Learning and Applications Guangdong Key Lab. of Intelligent Information Processing Shenzhen University China Institute for Intelligent Systems Research and Innovation Deakin University Australia College of Computer Science and Software Engineering Guangdong Key Lab. of Intelligent Information Processing Shenzhen University China School of Computer Science and Engineering Southern University of Science and Technology China

The Artificial Fish Swarm Algorithm (AFSA) is inspired by the ecological behaviors of fish schooling in nature, viz., the preying, swarming and following behaviors. Owing to a number of salient properties, which include flexibility, fast convergence, and insensitivity to the initial parameter settings, the family of AFSA has emerged as an effective Swarm Intelligence (SI) methodology that has been widely applied to solve real-world optimization problems. Since its introduction in 2002, many improved and hybrid AFSA models have been developed to tackle continuous, binary, and combinatorial optimization problems. This paper aims to present a concise review of the continuous AFSA, encompassing the original ASFA, its improvements and hybrid models, as well as their associated applications. We focus on articles published in high-quality journals since 2013. Our review provides insights into AFSA parameters modifications, procedure and sub-functions. The main reasons for these enhancements and the comparison results with other hybrid methods are discussed. In addition, hybrid, multi-objective and dynamic AFSA models that have been proposed to solve continuous optimization problems are elucidated. We also analyse possible AFSA enhancements and highlight future research directions for advancing AFSA-based models. Copyright © 2020, The Authors. All rights reserved.

关键词： Multiobjective optimization

Hard instance learning for quantum adiabatic prime factorization

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Lin, Jian Zhang, Zhengfeng Zhang, Junping Li, Xiaopeng State Key Laboratory of Surface Physics Institute of Nanoelectronics and Quantum Computing Department of Physics Fudan University Shanghai200433 China Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai200433 China Shanghai Qi Zhi Institute AI Tower Xuhui District Shanghai200232 China

Prime factorization is a difficult problem with classical computing, whose exponential hardness is the foundation of Rivest-Shamir-Adleman (RSA) cryptography. With programmable quantum devices, adiabatic quantum computing has been proposed as a plausible approach to solve prime factorization, having promising advantage over classical computing. Here, we find there are certain hard instances that are consistently intractable for both classical simulated annealing and un-configured adiabatic quantum computing (AQC). Aiming at an automated architecture for optimal configuration of quantum adiabatic factorization, we apply a deep reinforcement learning (RL) method to configure the AQC algorithm. By setting the success probability of the worst-case problem instances as the reward to RL, we show the AQC performance on the hard instances is dramatically improved by RL configuration. The success probability also becomes more evenly distributed over different problem instances, meaning the configured AQC is more stable as compared to the un-configured case. Through a technique of transfer learning, we find prominent evidence that the framework of AQC configuration is scalable—the configured AQC as trained on five qubits remains working efficiently on nine qubits with a minimal amount of additional training cost. Copyright © 2021, The Authors. All rights reserved.

关键词： Factorization

QUBIQ: Uncertainty Quantification for Biomedical Image Segmentation Challenge

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Hongwei Bran Navarro, Fernando Ezhov, Ivan Bayat, Amirhossein Das, Dhritiman Kofler, Florian Shit, Suprosanna Waldmannstetter, Diana Paetzold, Johannes C. Hu, Xiaobin Wiestler, Benedikt Zimmer, Lucas Amiranashvili, Tamaz Prabhakar, Chinmay Berger, Christoph Weidner, Jonas Alonso-Basanta, Michelle Rashid, Arif Baid, Ujjwal Adel, Wesam Alis, Deniz Baheti, Bhakti Bai, Yingbin Bhat, Ishaan Cetindag, Sabri Can Chen, Wenting Cheng, Li Dutande, Prasad Dular, Lara Elattar, Mustafa A. Feng, Ming Gao, Shengbo Huisman, Henkjan Hu, Weifeng Innani, Shubham Ji, Wei Karimi, Davood Kuijf, Hugo J. Kwak, Jin Tae Le, Hoang Long Li, Xiang Lin, Huiyan Liu, Tongliang Ma, Jun Ma, Kai Ma, Ting Oksuz, Ilkay Holland, Robbie Oliveira, Arlindo L. Pal, Jimut Bahan Pei, Xuan Qiao, Maoying Saha, Anindo Selvan, Raghavendra Shen, Linlin Silva, Joao Lourenco Spiclin, Ziga Talbar, Sanjay Wang, Dadong Wang, Wei Wang, Xiong Wang, Yin Xi, Ruiling Xu, Kele Yang, Yanwu Yergin, Mert Yu, Shuang Zeng, Lingxi Zhang, YingLin Zhao, Jiachen Zheng, Yefeng Zukovec, Martin Do, Richard Becker, Anton Simpson, Amber Konukoglu, Ender Jakab, Andras Bakas, Spyridon Joskowicz, Leo Menze, Bjoern Department of Informatics Technical University of Munich Germany Athinoula A. Martinos Center for Biomedical Imaging Massachusetts General Hospital Harvard Medical School United States Department of Quantitative Biomedicine University of Zurich Switzerland University Children’s Hospital Zurich University of Zurich Switzerland Department of Radioncology and Radiation Theraphy Klinikum rechts der Isar Technical University of Munich Germany Department of Information Technology and Electrical Engineering ETH-Zurich Switzerland Department of Radiology Memorial Sloan Kettering Cancer Center New York City United States Department of Biomedical and Molecular Sciences Queen’s University Canada TranslaTUM - Central Institute for Translational Cancer Research Technical University of Munich Germany McGovern Institute Massachusetts Institute of Technology United States Institute for Diagnostic and Interventional Radiology Unveristy Zurich Hospital Switzerland BioMedIA Imperial College London United Kingdom Department of Radiation Oncology University of Pennsylvania PA United States University of Pennsylvania PA United States Department of Radiation Oncology Winship Cancer Institute of Emory University Georgia United States Nile University Cairo Egypt Department of Medical Sciences Acibadem University Istanbul Turkey Shri Guru Gobind Singhji Institute of Engineering and Technology Maharashtra Nanded India Trustworthy Machine Learning Lab University of Sydney Australia Image Sciences Institute University Medical Center Utrecht Netherlands Computer Engineering Department Istanbul Technical University Istanbul Turkey School of Computer Science Shenzhen University Shenzhen China University of Alberta United States University of Ljubljana Faculty of Electrical Engineering Ljubljana Slovenia Tongji University Shanghai China OPPO Research Institute Shanghai China School of Biological and Medical Engineering Beihang University Beijing China Harvard Medical School Boston

Uncertainty in medical image segmentation tasks, especially inter-rater variability, arising from differences in interpretations and annotations by various experts, presents a significant challenge in achieving consistent and reliable image segmentation. This variability not only reflects the inherent complexity and subjective nature of medical image interpretation but also directly impacts the development and evaluation of automated segmentation algorithms. Accurately modeling and quantifying this variability is essential for enhancing the robustness and clinical applicability of these algorithms. We report the set-up and summarize the benchmark results of the Quantification of Uncertainties in Biomedical Image Quantification Challenge (QUBIQ), which was organized in conjunction with International Conferences on Medical Image Computing and computer-Assisted Intervention (MICCAI) 2020 and 2021. The challenge focuses on the uncertainty quantification of medical image segmentation which considers the omnipresence of inter-rater variability in imaging datasets. The large collection of images with multi-rater annotations features various modalities such as MRI and CT;various organs such as the brain, prostate, kidney, and pancreas;and different image dimensions 2D-vs-3D. A total of 24 teams submitted different solutions to the problem, combining various baseline models, Bayesian neural networks, and ensemble model techniques. The obtained results indicate the importance of the ensemble models, as well as the need for further research to develop efficient 3D methods for uncertainty quantification methods in 3D segmentation tasks. © 2024, CC BY-NC-ND.

关键词： Image segmentation

Estimation of perceptual scales using ordinal embedding

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Haghiri, Siavash Wichmann, Felix von Luxburg, Ulrike Department of Computer Science University of Tübingen Germany Neural Information Processing Group University of Tübingen Germany

In this paper we address the problem of measuring and analysing sensation, the subjective magnitude of one’s experience. We do this in the context of the method of triads: the sensation of the stimulus is evaluated via relative judgments of the form: "Is stimulus Si more similar to stimulus Sj or to stimulus Sk?". We propose to use ordinal embedding methods from machine learning to estimate the scaling function from the relative judgments. We review two relevant and well-known methods in psychophysics which are partially applicable in our setting: non-metric multi-dimensional scaling (NMDS) and the method of maximum likelihood difference scaling (MLDS). We perform an extensive set of simulations, considering various scaling functions, to demonstrate the performance of the ordinal embedding methods. We show that in contrast to existing approaches our ordinal embedding approach allows, first, to obtain reasonable scaling function from comparatively few relative judgments, second, the estimation of non-monotonous scaling functions, and, third, multi-dimensional perceptual scales. In addition to the simulations, we analyse data from two real psychophysics experiments using ordinal embedding methods. Our results show that in the one-dimensional, monotonically increasing perceptual scale our ordinal embedding approach works as well as MLDS, while in higher dimensions, only our ordinal embedding methods can produce a desirable scaling function. To make our methods widely accessible, we provide an R-implementation and general rules of thumb on how to use ordinal embedding in the context of psychophysics. Copyright © 2019, The Authors. All rights reserved.

关键词： Embeddings

Comparison-based framework for psychophysics: lab versus crowdsourcing

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Haghiri, Siavash Rubisch, Patricia Geirhos, Robert Wichmann, Felix von Luxburg, Ulrike Department of Computer Science University of Tübingen Germany Neural Information Processing Group University of Tübingen Germany

Traditionally, psychophysical experiments are conducted by repeated measurements on a few well-trained participants under well-controlled conditions, often resulting in, if done properly, high quality data. In recent years, however, crowdsourcing platforms are becoming increasingly popular means of data collection, measuring many participants at the potential cost of obtaining data of worse quality. In this paper we study whether the use of comparison-based (ordinal) data, combined with machine learning algorithms, can boost the reliability of crowdsourcing studies for psychophysics, such that they can achieve performance close to a lab experiment. To this end, we compare three setups: Simulations, a psychophysics lab experiment, and the same experiment on Amazon Mechanical Turk. All these experiments are conducted in a comparison-based setting where participants have to answer triplet questions of the form "is object x closer to y or to z?". We then use machine learning to solve the triplet prediction problem: Given a subset of triplet questions with corresponding answers, we predict the answer to the remaining questions. Considering the limitations and noise on MTurk, we find that the accuracy of triplet prediction is surprisingly close-but not equal-to our lab study. Copyright © 2019, The Authors. All rights reserved.

关键词： Crowdsourcing

Reconfigurable Intelligent Computational Surfaces: When Wave Propagation Control Meets Computing

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Yang, Bo Cao, Xuelin Xu, Jindan Huang, Chongwen Alexandropoulos, George C. Dai, Linglong Debbah, Mérouane Poor, H. Vincent Yuen, Chau The Engineering Product Development Pillar Singapore University of Technology and Design Singapore487372 Singapore The College of Information Science and Electronic Engineering Zhejiang Provincial Key Lab of information processing communication and networking Zhejiang University Hangzhou310007 China International Joint Innovation Center Zhejiang University Haining314400 China The Department of Informatics and Telecommunications National and Kapodistrian University of Athens Athens15784 Greece The Technology Innovation Institute Masdar City Abu Dhabi9639 United Arab Emirates The Department of Electronic Engineering Tsinghua University Beijing100084 China CentraleSupelec University Paris-Saclay Gif-sur-Yvette91192 France Department of Electrical and Computer Engineering Princeton University NJ United States

The envisioned sixth-generation (6G) of wireless networks will involve an intelligent integration of communications and computing, thereby meeting the urgent demands of diverse applications. To realize the concept of the smart radio environment, reconfigurable intelligent surfaces (RISs) are a promising technology for offering programmable propagation of impinging electromagnetic signals via external control. However, the purely reflective nature of conventional RISs induces significant challenges in supporting computation-based applications, e.g., wave-based calculation and signal processing. To fulfil future communication and computing requirements, new materials are needed to complement the existing technologies of metasurfaces, enabling further diversification of electronics and their applications. In this event, we introduce the concept of reconfigurable intelligent computational surface (RICS), which is composed of two reconfigurable multifunctional layers: the ‘reconfigurable beamforming layer’ which is responsible for tunable signal reflection, absorption, and refraction, and the ‘intelligence computation layer’ that concentrates on metamaterials-based computing. By exploring the recent trends on computational metamaterials, RICSs have the potential to make joint communication and computation a reality. We further demonstrate two typical applications of RICSs for performing wireless spectrum sensing and secrecy signal processing. Future research challenges arising from the design and operation of RICSs are finally highlighted. Copyright © 2022, The Authors. All rights reserved.

关键词： Metamaterials

Computational modeling of ketamine-induced changes in gamma-band oscillations: The contribution of parvalbumin and somatostatin interneurons

学校读者我要写书评

暂无评论

PLOS Computational Biology 2025年第6 June期21卷 e1013118页

作者： Rademacher, Jessie Grent-'t-Jong, Tineke Rivolta, Davide Sauer, Andreas Scheller, Bertram Gonzalez-Burgos, Guillermo Metzner, Christoph Uhlhaas, Peter J. Department of Child and Adolescent Psychiatry Charité Universitätsmedizin Berlin Germany Department of Education Psychology and Communication University of Bari Aldo Moro Bari Italy Max Planck Institute for Brain Research Frankfurt am Main Germany for Neuroscience in Cooperation with Max Planck Society Frankfurt am Main Germany SRH University Department of Applied Psychology Heidelberg Germany Department of Anesthesiology and Intensive Care Medicine St. Josefs Hospital Wiesbaden Germany Department of Psychiatry University of Pittsburgh PittsburghPA United States Neural Information Processing Group Institute of Software Engineering and Theoretical Computer Science Technische Universität Berlin Berlin Germany School of Physics Engineering and Computer Science University of Hertfordshire Hatfield United Kingdom

Ketamine, an NMDA receptor (NMDA-R) antagonist, produces psychotomimetic effects when administered in sub-anesthetic dosages. While previous research suggests that Ketamine alters the excitation/inhibition (E/I)-balance in cortical microcircuits, the precise neural mechanisms by which Ketamine produces these effects are not well understood. We analyzed resting-state MEG data from n = 12 participants who were administered Ketamine to assess changes in gamma-band (30–90 Hz) power and the slope of the aperiodic power spectrum compared to placebo. In addition, correlations of these effects with gene-expression of GABAergic interneurons and NMDA-Rs subunits were analyzed. Finally, we compared Ketamine-induced spectral changes to the effects of systematically changing NMDA-R levels on pyramidal cells, and parvalbumin-, somatostatin- and vasoactive intestinal peptide-expressing interneurons in a computational model of cortical layer-2/3 to identify crucial sites of Ketamine action. Ketamine resulted in a flatter aperiodic slope and increased gamma-band power across brain regions, with pronounced effects in prefrontal and central areas. These effects were correlated with the spatial distribution of parvalbumin and GluN2D gene expression. Computational modeling revealed that reduced NMDA-R activity in parvalbumin or somatostatin interneurons could reproduce increased gamma-band power by increasing pyramidal neuron firing rate, but did not account for changes in the aperiodic slope. The results suggest that parvalbumin and somatostatin interneurons may underlie increased gamma-band power following Ketamine administration in healthy volunteers, while changes in the aperiodic component could not be recreated. These findings have implications for current models of E/I-balance, as well as for understanding the mechanisms underlying the circuit effects of Ketamine. This is an open access article, free of all copyright, and may be freely reproduced, distributed, transmitted, modifi

关键词： Transcription