检索结果-内蒙古大学图书馆

Spectrum Allocation Exploiting Different Core Selection Patterns for Graceful Degradation of Inter-Core Crosstalk in Space-Division Multiplexing Elastic Optical Networks

学校读者我要写书评

暂无评论

Spectrum Allocation Exploiting Different Core Selection Patt...

Photonics in Switching and Computing, PSC 2021

作者： Seki, Yuya Tanigawa, Yosuke Hirota, Yusuke Tode, Hideki Department of Computer Science and Intelligent Systems Osaka Prefecture University 1-1 Gakuen-cho Naka-ku Sakai-shi Osaka599-8531 Japan National Institute of Information and Communications Technology 4-2-1 Nukui-Kitamachi Koganei Tokyo184-8795 Japan

We propose a spectrum allocation for graceful degradation of intercore crosstalk in space-division multiplexed elastic optical networks, which utilizes precalculated thresholds based on coupled power theory with multi...

ISBN: (纸本)9781557528209

关键词：

Specialists outperform generalists in ensemble classification

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Meyen, Sascha Göppert, Frieder Alber, Helen Von Luxburg, Ulrike Franz, Volker H. Department of Computer Science University of Tübingen Tübingen Germany Max Planck Institute for Intelligent Systems Tübingen Germany

Consider an ensemble of k individual classifiers whose accuracies are known. Upon receiving a test point, each of the classifiers outputs a predicted label and a confidence in its prediction for this particular test point. In this paper, we address the question of whether we can determine the accuracy of the ensemble. Surprisingly, even when classifiers are combined in the statistically optimal way in this setting, the accuracy of the resulting ensemble classifier cannot be computed from the accuracies of the individual classifiers-as would be the case in the standard setting of confidence weighted majority voting. We prove tight upper and lower bounds on the ensemble accuracy. We explicitly construct the individual classifiers that attain the upper and lower bounds: specialists and generalists. Our theoretical results have very practical consequences: (1) If we use ensemble methods and have the choice to construct our individual (independent) classifiers from scratch, then we should aim for specialist classifiers rather than generalists. (2) Our bounds can be used to determine how many classifiers are at least required to achieve a desired ensemble accuracy. Finally, we improve our bounds by considering the mutual information between the true label and the individual classifier's output. © 2021, CC BY.

关键词： Classification (of information)

Regularly Truncated M-estimators for Learning with Noisy Labels

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Xia, Xiaobo Lu, Pengqian Gong, Chen Han, Bo Yu, Jun Yu, Jun Liu, Tongliang The Sydney AI Center School of Computer Science Faculty of Engineering The University of Sydney DarlingtonNSW2008 Australia The Australian AI Institute Faculty of Engineering and IT The University of Technology Sydney BroadwayNSW2007 Australia The PCA Lab The Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China The Department of Computing Hong Kong Polytechnic University Hong Kong The Department of Computer Science Hong Kong Baptist University Hong Kong The School of Computer Science and Technology Hangzhou Dianzi University Hangzhou310018 China The Department of Automation University of Science and Technology of China Hefei230026 China

The sample selection approach is very popular in learning with noisy labels. As deep networks "learn pattern first", prior methods built on sample selection share a similar training procedure: the small-loss examples can be regarded as clean examples and used for helping generalization, while the large-loss examples are treated as mislabeled ones and excluded from network parameter updates. However, such a procedure is arguably debatable from two folds: (a) it does not consider the bad influence of noisy labels in selected small-loss examples;(b) it does not make good use of the discarded large-loss examples, which may be clean or have meaningful information for generalization. In this paper, we propose regularly truncated M-estimators (RTME) to address the above two issues simultaneously. Specifically, RTME can alternately switch modes between truncated M-estimators and original M-estimators. The former can adaptively select small-losses examples without knowing the noise rate and reduce the side-effects of noisy labels in them. The latter makes the possibly clean examples but with large losses involved to help generalization. Theoretically, we demonstrate that our strategies are label-noise-tolerant. Empirically, comprehensive experimental results show that our method can outperform multiple baselines and is robust to broad noise types and levels. The implementation is available at https://***/xiaoboxia/RTM_LNL. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

High-dimensional gaussian process inference with derivatives

学校读者我要写书评

暂无评论

arXiv 2021年

作者： de Roos, Filip Gessner, Alexandra Hennig, Philipp Department of Computer Science University of Tübingen Tübingen Germany Max Planck Institute for Intelligent Systems Tübingen Germany

Although it is widely known that Gaussian processes can be conditioned on observations of the gradient, this functionality is of limited use due to the prohibitive computational cost of O(N3D3) in data points N and dimension D. The dilemma of gradient observations is that a single one of them comes at the same cost as D independent function evaluations, so the latter are often preferred. Careful scrutiny reveals, however, that derivative observations give rise to highly structured kernel Gram matrices for very general classes of kernels (inter alia, stationary kernels). We show that in the low-data regime N 2D+(N2)3) (i.e., linear in the number of dimensions) and, in special cases, to O(N2D+N3). This reduction in complexity opens up new use-cases for inference with gradients especially in the high-dimensional regime, where the information-to-cost ratio of gradient observations significantly increases. We demonstrate this potential in a variety of tasks relevant for machine learning, such as optimization and Hamiltonian Monte Carlo with predictive gradients. Copyright © 2021, The Authors. All rights reserved.

关键词： Gaussian noise (electronic)

6D Movable Antenna Enhanced Interference Mitigation for Cellular-Connected UAV Communications

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ren, Tianshi Zhang, Xianchao Zhu, Lipeng Ma, Wenyan Gao, Xiaozheng Zhang, Rui School of Information and Electronics Beijing Institute of Technology Beijing100081 China Department of Electrical and Computer Engineering National University of Singapore Singapore117583 Singapore Provincial Key Laboratory of Multimodal Perceiving and Intelligent Systems Jiaxing University Jiaxing314001 China Engineering Research Center of Intelligent Human Health Situation Awareness of Zhejiang Province Jiaxing University Jiaxing314001 China School of Science and Engineering Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Guangdong Shenzhen518172 China

Cellular-connected unmanned aerial vehicle (UAV) communications is an enabling technology to transmit control signaling or payload data for UAVs through cellular networks. Due to the line-of-sight (LoS) dominant air-to-ground channels, efficient interference mitigation is crucial to UAV communications, while the conventional fixed-position antenna (FPA) arrays have limited degrees of freedom (DoFs) to suppress the interference between the UAV and its non-associated co-channel base stations (BSs). To address this challenge, we propose in this letter a new approach by utilizing the six-dimensional movable antenna (6DMA) arrays to enhance the interference mitigation for the UAV. Specifically, we propose an efficient block coordinate descent (BCD) algorithm to iteratively optimize the antenna position vector (APV), array rotation vector (ARV), receive beamforming vector, and associated BS of the UAV to maximize its signal-to-interference-plus-noise ratio (SINR). Numerical results show that the proposed 6DMA enhanced cellular-connected UAV communication can significantly outperform that with the traditional FPA arrays and other benchmark schemes in terms of interference mitigation. Copyright © 2024, The Authors. All rights reserved.

关键词： Signal to noise ratio

Prediction of endometrial cancer MRI images based on deep learning and improved Bayesian extreme learning machine ensemble learning

学校读者我要写书评

暂无评论

Prediction of endometrial cancer MRI images based on deep le...

Frontiers Technology of Information and computer (ICFTIC), IEEE International Conference on

作者： Ximiao Wang Qinghui Hu Xisheng Dai Peijun Li Yuan Chen Institute of Intelligent Systems and Control Guangxi University of Science and Technology Liuzhou City Guangxi Province China School of Computer Science and Engineering Guilin University of Aerospace Technology Guilin City Guangxi Province China Department of Radiology Jiangmen Central Hospital Jiangmen City Guangdong Province China Department of Gynecology Jiangmen Central Hospital Jiangmen City Guangdong Province China

For the prediction of deep myometrial invasion (DMI) in endometrial cancer (EC), this study proposes an ensemble learning method which combines deep learning (DL) and improved Bayesian extreme learning machine (BELM). Firstly, the MRI images of endometrial cancer are preprocessed to meet the requirements. Secondly, the deep features relevant to the task are extracted from the images by using convolutional kernels. Finally, the bootstrap resampling method is employed to repeatedly sample multiple training subsets from the training set. The improved Bayesian extreme learning machine is used as the base classifier to train multiple independent sub-models. An ensemble learning classifier is constructed using an ensemble strategy to improve the prediction accuracy and stability of the model. Experimental results show that the proposed method achieves an AUC of 0.758 on the internal validation set and 0.740 on the external validation set, which demonstrat good generalization ability and stability of the proposed method.

关键词：

SPL: A Socratic Playground for Learning Powered by Large Language Model

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Liang Lin, Jionghao Kuang, Ziyi Xu, Sheng Hu, Xiangen Institute for Intelligent Systems University of Memphis MemphisTN38152 United States Department of Electrical and Computer Engineering University of Memphis MemphisTN38152 United States School of Computer Science Carnegie Mellon University PittsburghPA15213 United States School of Psychology Shaanxi Normal University Xi’an710062 China School of Psychology Central China Normal University Wuhan430079 China Department of Applied Social Sciences Hong Kong Polytechnic University Hong Kong

Dialogue-based intelligent Tutoring systems (ITSs) have significantly advanced adaptive and personalized learning by automating sophisticated human tutoring strategies within interactive dialogues. However, replicating the nuanced patterns of expert human communication remains a challenge in Natural Language Processing (NLP). Recent advancements in NLP, particularly Large Language Models (LLMs) such as OpenAI’s GPT-4, offer promising solutions by providing human-like and context-aware responses based on extensive pre-trained knowledge. Motivated by the effectiveness of LLMs in various educational tasks (e.g., content creation and summarization, problem-solving, and automated feedback provision), our study introduces the Socratic Playground for Learning (SPL), a dialogue-based ITS powered by the GPT-4 model, which employs the Socratic teaching method to foster critical thinking among learners. Through extensive prompt engineering, SPL can generate specific learning scenarios and facilitates efficient multi-turn tutoring dialogues. The SPL system aims to enhance personalized and adaptive learning experiences tailored to individual needs, specifically focusing on improving critical thinking skills. Our pilot experimental results from essay writing tasks demonstrate SPL has the potential to improve tutoring interactions and further enhance dialogue-based ITS functionalities. Our study, exemplified by SPL, demonstrates how LLMs enhance dialogue-based ITSs and expand the accessibility and efficacy of educational technologies. © 2024, CC BY.

关键词： Contrastive Learning

Depth Estimation of the Object of Interest in Challenging Cross-Domain Scenes

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Xu, Chenglong Chen, Chu Xing, Wen Herrera-Viedma, Enrique College of Intelligent Systems Science and Engineering Harbin Engineering University Harbin150001 China Qingdao Innovation and Development Center Harbin Engineering University Qingdao266000 China Shenyang SIASUN Robot & Automation Co. LTD Shenyang110168 China Andalusian Research Institute of Data Science and Computational Intelligence Department of Computer Science and AI University of Granada Granada18071 Spain

Depth estimation plays an important role in 3D visual perception, autonomous vehicles, and near-field optical detection. At present, there are mainly learning-based methods and traditional geometric constraint reasoning based methods. However, most learning-based methods have poor cross-domain generalization, the accuracy will be greatly reduced when tested on new scenes. Although the traditional geometric methods have strong scene adaptability, they have more marginal noise in depth discontinuity areas, and require a large amount of memory at a high bandwidth. In order to solve the above problems, we present a disparity confidence propagation and edge smoothing framework, which combines robust semantic mask with tree diffusion model. Compared with those of state-of-the-art fast geometric constraint based methods and learning-based methods, the proposed method has a great improvement in cross-domain adaptability and efficiency. Experiments on multiple data sets verify the effectiveness of the method, and a good balance is achieved between generalization and accuracy. © 2023, The Authors. All rights reserved.

关键词： Semantics

Non-convex potential games for finding global solutions to sensor network localization

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Xu, Gehui Chen, Guanpu Hong, Yiguang Fidan, Baris Parisini, Thomas Johansson, Karl H. Key Laboratory of Systems and Control Academy of Mathematics and Systems Science Beijing China Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm100 44 Sweden Department of Control Science and Engineering Tongji University Shanghai201804 China Shanghai Research Institute for Intelligent Autonomous Systems Shanghai201210 China Department of Mechanical and Mechatronics Engineering University of Waterloo WaterlooONN2L 3G1 Canada Department of Electrical and Electronic Engineering Imperial College London LondonSW7 2AZ United Kingdom Department of Engineering and Architecture University of Trieste Trieste34127 Italy

Sensor network localization (SNL) problems require determining the physical coordinates of all sensors in a network. This process relies on the global coordinates of anchors and the available measurements between non-anchor and anchor nodes. Attributed to the intrinsic non-convexity, obtaining a globally optimal solution to SNL is challenging, as well as implementing corresponding algorithms. In this paper, we formulate a non-convex multi-player potential game for a generic SNL problem to investigate the identification condition of the global Nash equilibrium (NE) therein, where the global NE represents the global solution of SNL. We employ canonical duality theory to transform the non-convex game into a complementary dual problem. Then we develop a conjugation-based algorithm to compute the stationary points of the complementary dual problem. On this basis, we show an identification condition of the global NE: the stationary point of the proposed algorithm satisfies a duality relation. Finally, simulation results are provided to validate the effectiveness of the theoretical results. Copyright © 2023, The Authors. All rights reserved.

关键词： Sensor networks