检索结果-内蒙古大学图书馆

Interval Markov decision processes with multiple objectives: From Robust strategies to Pareto curves

学校读者我要写书评

暂无评论

Interval Markov decision processes with multiple objectives:...

作者： Hahn, Ernst Moritz Hashemi, Vahid Hermanns, Holger Lahijanian, Morteza Turrini, Andrea School of Electronics Electrical Engineering and Computer Science Queen's University Belfast Belfast United Kingdom State Key Laboratory of Computer Science Institute of Software CAS Beijing China Department of Information Technology Audi AG Ingolstadt Germany Saarland University Saarland Informatics Campus Saarbrücken Germany Institute of Intelligent Software Guangzhou Guangzhou China Department of Smead Aerospace Engineering and Sciences University of Colorado BoulderCO United States

Accurate Modelling of a real-world system with probabilistic behaviour is a difficult task. Sensor noise and statistical estimations, among other imprecisions, make the exact probability values impossible to obtain. In this article, we consider Interval Markov decision processes (IMDPs), which generalise classical MDPs by having interval-valued transition probabilities. They provide a powerful modelling tool for probabilistic systems with an additional variation or uncertainty that prevents the knowledge of the exact transition probabilities. We investigate the problem of robust multi-objective synthesis for IMDPs and Pareto curve analysis of multi-objective queries on IMDPs. We study how to find a robust (randomised) strategy that satisfies multiple objectives involving rewards, reachability, and more general ω-regular properties against all possible resolutions of the transition probability uncertainties, as well as to generate an approximate Pareto curve providing an explicit view of the trade-offs between multiple objectives. We show that the multi-objective synthesis problem is PSPACE-hard and provide a value iteration-based decision algorithm to approximate the Pareto set of achievable points. We finally demonstrate the practical effectiveness of our proposed approaches by applying them on several case studies using a prototype tool. © 2019 Copyright held by the owner/author(s).

关键词： Multiobjective optimization

Investigating Bi-level optimization for learning and vision from a unified perspective: A survey and beyond

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Liu, Risheng Gao, Jiaxin Zhang, Jin Meng, Deyu Lin, Zhouchen DUT-RU International School of Information Science & Engineering Dalian University of Technology Key Laboratory for Ubiquitous Network Service Software of Liaoning Province Dalian116024 China Department of Mathematics Southern University of Science and Technology National Center for Applied Mathematics Shenzhen China School of Mathematics and Statistics Ministry of Education Key Lab of Intelligent Networks and Network Security Xi’an Jiaotong University Xi’an Shaanxi China School of Electronics Engineering and Computer Science Peking University Beijing100871 China Cooperative Medianet Innovation Center Shanghai Jiao Tong University Shanghai200240 China

Bi-Level Optimization (BLO) is originated from the area of economic game theory and then introduced into the optimization community. BLO is able to handle problems with a hierarchical structure, involving two levels of optimization tasks, where one task is nested inside the other. In machine learning and computer vision fields, despite the different motivations and mechanisms, a lot of complex problems, such as hyper-parameter optimization, multi-task and meta learning, neural architecture search, adversarial learning and deep reinforcement learning, actually all contain a series of closely related subproblms. In this paper, we first uniformly express these complex learning and vision problems from the perspective of BLO. Then we construct a best-response-based single-level reformulation and establish a unified algorithmic framework to understand and formulate mainstream gradient-based BLO methodologies, covering aspects ranging from fundamental automatic differentiation schemes to various accelerations, simplifications, extensions and their convergence and complexity properties. Last but not least, we discuss the potentials of our unified BLO framework for designing new algorithms and point out some promising directions for future research. © 2021, CC BY.

关键词： Deep learning

Slide-based Graph Collaborative Training for Histopathology Whole Slide Image Analysis

学校读者我要写书评

暂无评论

IEEE Transactions on Medical Imaging 2025年

作者： Shi, Jun Shu, Tong Jiang, Zhiguo Wang, Wei Wu, Haibo Zheng, Yushan Hefei University of Technology School of Software Hefei230601 China Hefei University of Technology School of Computer Science and Information Engineering Hefei230601 China School of Astronautics Beihang University Image Processing Center Beijing102206 China Beihang University Tianmushan Laboratory Zhejiang Hangzhou311115 China University of Science and Technology of China Division of Life Sciences and Medicine Department of Pathology the First Affiliated Hospital of USTC Hefei230036 China University of Science and Technology of China Division of Life Sciences and Medicine Intelligent Pathology Institute Hefei230036 China Beihang University School of Engineering Medicine Beijing Advanced Innovation Center on Biomedical Engineering Beijing100191 China

The development of computational pathology lies in the consensus that pathological characteristics of tumors are significant guidance for cancer diagnostics. Most existing research focuses on the inner-contextual information within each WSI yet ignores the possible inter-correlations between slides. As the development of tumors is a continuous process involving a series of histological, morphological, and genetic changes that accumulate over time, the similarities and differences between WSIs across various stages, grades, locations and patients should potentially contribute to the representation of WSIs and deserve to be taken into account in WSI modeling. To verify the advancement of introducing the slide inter-correlations into the representation learning of WSIs, we proposed a generic WSI analysis pipeline SlideGCD that can be adapted to any existing Multiple Instance Learning (MIL) frameworks and improve their performance. With the new paradigm, the prior knowledge of cancer development can participate in the end-to-end workflow, which concurrently initializes and refines the slide representation, as a guide for message passing in the slide-based graph. Extensive comparisons and experiments are conducted to validate the effectiveness and robustness of the proposed pipeline across 4 different tasks, including cancer subtyping, cancer staging, survival prediction, and genemutation prediction, with 8 representative SOTA WSI analysis frameworks as backbones. © 1982-2012 IEEE.

关键词： Image correlation

F2A2: Flexible Fully-decentralized Approximate Actor-critic for Cooperative Multi-agent Reinforcement Learning

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Li, Wenhao Jin, Bo Wang, Xiangfeng Yan, Junchi Zha, Hongyuan School of Data Science The Chinese University of Hong Kong Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518172 China School of Software Engineering Shanghai Research Institute for Intelligent Autonomous Systems Tongji University Shanghai201804 China School of Computer Science and Technology Key Laboratory of Mathematics and Engineering Applications Ministry of Education East China Normal University Shanghai200062 China Department of Computer Science and Engineering Key Laboratory of Artificial Intelligence Ministry of Education Shanghai Jiao Tong University Shanghai200240 China

Traditional centralized multi-agent reinforcement learning (MARL) algorithms are sometimes unpractical in complicated applications due to non-interactivity between agents, the curse of dimensionality, and computation complexity. Hence, several decentralized MARL algorithms are motivated. However, existing decentralized methods only handle the fully cooperative setting where massive information needs to be transmitted in training. The block coordinate gradient descent scheme they used for successive independent actor and critic steps can simplify the calculation, but it causes serious bias. This paper proposes a flexible fully decentralized actor-critic MARL framework, which can combine most of the actor-critic methods and handle large-scale general cooperative multi-agent settings. A primal-dual hybrid gradient descent type algorithm framework is designed to learn individual agents separately for decentralization. From the perspective of each agent, policy improvement and value evaluation are jointly optimized, which can stabilize multi-agent policy learning. Furthermore, the proposed framework can achieve scalability and stability for the large-scale environment. This framework also reduces information transmission by the parameter sharing mechanism and novel modeling-other-agents methods based on theory-of-mind and online supervised learning. Sufficient experiments in cooperative Multiagent Particle Environment and StarCraft II show that the proposed decentralized MARL instantiation algorithms perform competitively against conventional centralized and decentralized methods. Copyright © 2020, The Authors. All rights reserved.

关键词： Gradient methods

Face Analysis for Coronary Heart Disease Diagnosis 12

学校读者我要写书评

暂无评论

Face Analysis for Coronary Heart Disease Diagnosis

12th International Congress on Image and Signal Processing, BioMedical engineering and Informatics, CISP-BMEI 2019

作者： Lin, Shisong Zhuang, Xiaodong Huang, Shiyun Liu, Yahui Shen, Linlin Liao, Xinxue Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China Cardiology department First affiliated hospital of Sun Yat-sen University Guangzhou China NHC Key Laboratory of Assisted Circulation Sun Yat-sen University Guangzhou China Shenzhen National Medical Science and Technology Co. Ltd. Shenzhen China

ISBN: (纸本)9781728148526

CHD (Coronary Heart Disease) is one of the leading causes of cardiovascular disease deaths. Invasive coronary arteriography is one of the widely used approaches to diagnose CHD. However, the time cost and expenses for most of the diagnosis methodologies are high and some patients are reluctant to do such a diagnosis. In this paper, we aim to develop a novel low cost method to predict CHD. As suggested by the cardiologists, there are substantial differences between the facial images of patients with CHD and those of healthy subjects. In this paper, we conduct an automatic analysis of the texture features extracted from eight ROIs (Regions of Interests) of the face images. Based on the texture features, random forest and decision tree are used to predict whether the subject has a CHD, or not. The experimental results on a set of 1528 face images collected from 309 subjects suggest that, our approach achieved a promising, i.e. 72.73%, prediction accuracy. © 2019 IEEE.

关键词： Diagnosis

Knowledge-routed visual question reasoning: Challenges for deep representation embedding

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Cao, Qingxing Li, Bailin Liang, Xiaodan Wang, Keze Lin, Liang School of Intelligent Systems Engineering Sun Yat-sen University China DarkMatter AI Research China Department of statistics University of California Los AngelesCA90095 United States School of Computer Science and Engineering Sun Yat-sen University Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Engineering Research Center for Advanced Computing Engineering Software of Ministry of Education China

Though beneficial for encouraging the Visual Question Answering (VQA) models to discover the underlying knowledge by exploiting the input-output correlation beyond image and text contexts, the existing knowledge VQA datasets are mostly annotated in a crowdsource way, e.g., collecting questions and external reasons from different users via the internet. In addition to the challenge of knowledge reasoning, how to deal with the annotator bias also remains unsolved, which often leads to superficial over-fitted correlations between questions and answers. To address this issue, we propose a novel dataset named Knowledge-Routed Visual Question Reasoning for VQA model evaluation. Considering that a desirable VQA model should correctly perceive the image context, understand the question, and incorporate its learned knowledge, our proposed dataset aims to cutoff the shortcut learning exploited by the current deep embedding models and push the research boundary of the knowledge-based visual question reasoning. Specifically, we generate the question-answer pair based on both the Visual Genome scene graph and an external knowledge base with controlled programs to disentangle the knowledge from other biases. The programs can select one or two triplets from the scene graph or knowledge base to push multi-step reasoning, avoid answer ambiguity, and balanced the answer distribution. In contrast to the existing VQA datasets, we further imply the following two major constraints on the programs to incorporate knowledge reasoning: i) multiple knowledge triplets can be related to the question, but only one knowledge relates to the image object. This can enforce the VQA model to correctly perceive the image instead of guessing the knowledge based on the given question solely;ii) all questions are based on different knowledge, but the candidate answers are the same for both the training and test sets. We make the testing knowledge unused during training to evaluate whether a model can unde

关键词： Knowledge based systems

Deep Learning in Digital Breast Tomosynthesis: Current Status, Challenges, and Future Trends

学校读者我要写书评

暂无评论

MedComm

MedComm 2025年第6期6卷 e70247页

作者： Ruoyun Wang Fanxuan Chen Haoman Chen Chenxing Lin Jincen Shuai Yutong Wu Lixiang Ma Xiaoqu Hu Min Wu Jin Wang Qi Zhao Jianwei Shuai Jingye Pan Oujiang Laboratory (Zhejiang Lab for Regenerative Medicine Vision and Brain Health) Wenzhou Institute University of Chinese Academy of Sciences Wenzhou China Wenzhou Medical University Wenzhou China UCSC Baskin School of Engineering University of California Santa Cruz California USA Department of Anatomy Histology & Embryology School of Basic Medical Sciences Fudan University Shanghai China Department of Medicine Harvard Medical School and Brigham and Women's Hospital Boston Massachusetts USA Joint Research Centre on Medicine The Affiliated Xiangshan Hospital of Wenzhou Medical University Ningbo China Stony Brook University Stony Brook New York USA School of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan China Key Laboratory of Intelligent Treatment and Life Support for Critical Diseases of Zhejiang Province Wenzhou China Department of Big Data in Health Science The First Affiliated Hospital of Wenzhou Medical University Wenzhou China Zhejiang Engineering Research Center for Hospital Emergency and Process Digitization Wenzhou China

The high-resolution three-dimensional (3D) images generated with digital breast tomosynthesis (DBT) in the screening of breast cancer offer new possibilities for early disease diagnosis. Early detection is especially important as the incidence of breast cancer increases. However, DBT also presents challenges in terms of poorer results for dense breasts, increased false positive rates, slightly higher radiation doses, and increased reading times. Deep learning (DL) has been shown to effectively increase the processing efficiency and diagnostic accuracy of DBT images. This article reviews the application and outlook of DL in DBT-based breast cancer screening. First, the fundamentals and challenges of DBT technology are introduced. The applications of DL in DBT are then grouped into three categories: diagnostic classification of breast diseases, lesion segmentation and detection, and medical image generation. Additionally, the current public databases for mammography are summarized in detail. Finally, this paper analyzes the main challenges in the application of DL techniques in DBT, such as the lack of public datasets and model training issues, and proposes possible directions for future research, including large language models, multisource domain transfer, and data augmentation, to encourage innovative applications of DL in medical imaging.

关键词： early breast cancer screening digital breast tomosynthesis deep learning public database medical image analysis

ANDROIDOFF:Offloading android application based on cost estimation

学校读者我要写书评

暂无评论

Journal of Systems and software 2019年 158卷 110418-000页

作者： Chen, Xing Chen, Jiaqing Liu, Bichun Ma, Yun Zhang, Ying Zhong, Hao College of Mathematics and Computer Science Fuzhou University Fuzhou350116 China Fujian Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou350116 China School of Software Tsinghua University Beijing100084 China National Engineering Research Center of Software Engineering Peking University China Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai200240 China

Computation offloading is a promising way of improving the performance and reducing the battery power consumption, since it moves some time-consuming computation activities to nearby servers. Although various approaches have been proposed to support computation offloading, we argue that there is still sufficient space for improvements, since existing approaches cannot accurately estimate the execution costs. As a result, we find that their offloading plans are less optimized. To handle the problem, in this paper, given an Android application, we propose a novel approach, called ANDROIDOFF, that supports offloading at the granularity of objects. Supporting such capability is challenging due to the two reasons: (1) through dynamic execution, it is feasible to collect the execution costs of only partial methods, and (2) it is difficult to accurately estimate the execution costs of the remaining methods. To overcome the challenges, given an Android application, ANDROIDOFF first combines static and dynamic analysis to predict the execution costs of all its methods. After all the costs are estimated, ANDROIDOFF synthesizes an offloading plan, in which determines the offloading details. We evaluate ANDROIDOFF on a real-world application, with two mobile devices. Our results show that, compared with other approaches, ANDROIDOFF saves the response time by 8%–49% and reduces the energy consumption by 12%–49% on average for computation-intensive applications. © 2019 Elsevier Inc.

关键词： computation offloading

A review of uncertainty quantification in deep learning: Techniques, applications and challenges

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Abdar, Moloud Pourpanah, Farhad Hussain, Sadiq Rezazadegan, Dana Liu, Li Ghavamzadeh, Mohammad Fieguth, Paul Cao, Xiaochun Khosravi, Abbas Rajendra Acharya, U. Makarenkov, Vladimir Nahavandi, Saeid Deakin University Australia College of Mathematics and Statistics Guangdong Key Lab. of Intelligent Information Processing Shenzhen University Shenzhen518060 China Dibrugarh University Dibrugarh India Department of Computer Science and Software Engineering Swinburne University of Technology Melbourne Australia Center for Machine Vision and Signal Analysis University of Oulu Oulu Finland Google research United States Department of Systems Design Engineering University of Waterloo Waterloo Canada State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences Beijing China Department of Electronics and Computer Engineering Ngee Ann Polytechnic Clementi Singapore Department of Computer Science University of Quebec in Montreal MontrealQC Canada

—Uncertainty quantification (UQ) plays a pivotal role in the reduction of uncertainties during both optimization and decision making, applied to solve a variety of real-world applications in science and engineering. Bayesian approximation and ensemble learning techniques are two of the most widely-used UQ methods in the literature. In this regard, researchers have proposed different UQ methods and examined their performance in a variety of applications such as computer vision (e.g., self-driving cars and object detection), image processing (e.g., image restoration), medical image analysis (e.g., medical image classification and segmentation), natural language processing (e.g., text classification, social media texts and recidivism risk-scoring), bioinformatics, etc. This study reviews recent advances in UQ methods used in deep learning, investigates the application of these methods in reinforcement learning, and highlight the fundamental research challenges and directions associated with the UQ field. Copyright © 2020, The Authors. All rights reserved.

关键词： Image segmentation