检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Salvatori, Tommaso Mali, Ankur Buckley, Christopher L. Lukasiewicz, Thomas Rao, Rajesh P.N. Friston, Karl Ororbia, Alexander VERSES AI Research Lab Los AngelesCA United States Institute of Logic and Computation Vienna University of Technology Austria University of South Florida TampaFL33620 United States Sussex AI Group Department of Informatics University of Sussex Brighton United Kingdom Department of Computer Science University of Oxford United Kingdom Paul G. Allen School of Computer Science and Engineering University of Washington SeattleWA United States The Wellcome Centre for Human Neuroimaging Queen Square Institute of Neurology University College London United Kingdom The Neural Adaptive Computing Laboratory Rochester Institute of Technology RochesterNY14623 United States

Artificial intelligence (AI) is rapidly becoming one of the key technologies of this century. The majority of results in AI thus far have been achieved using deep neural networks trained with the error backpropagation learning algorithm. However, such an algorithm has always been considered biologically implausible. To this end, recent works have studied learning algorithms for deep neural networks inspired by the neurosciences. One such theory, called predictive coding (PC), has shown promising properties that make it potentially valuable for the machine learning community: it can model information processing in different areas of the brain, can be used in cognitive control and robotics, has a solid mathematical foundation in variational inference, and performs its computations asynchronously. Inspired by such properties, works that propose novel PC-like algorithms are starting to be present in multiple sub-fields of machine learning and artificial intelligence at large. Here, we survey such efforts by first providing a broad overview of the history of PC to provide a common ground for the understanding of the recent developments, then by surveying current efforts and results, and concluding with a large discussion of possible implications and ways forward. Copyright © 2023, The Authors. All rights reserved.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Semi-Decentralized Model for Drone Collaboration on Secure Measurement of Positions 5

Semi-Decentralized Model for Drone Collaboration on Secure M...

引用

5th International Conference on Future Networks and Distributed Systems: The Premier Conference on Smart Next Generation Networking Technologies, ICFNDS 2021

作者： Kara, Mostefa Laouid, Abdelkader Bounceur, Ahcene Hammoudeh, Mohammad Alshaikh, Muath Kebache, Romaissa Liap Laboratory El Oued University PO Box 789 El Oued39000 Algeria Lab-STICC Umr Cnrs University of Western Brittany Ubo Brest6285 France School of Computing Mathematics and Digital Technology Manchester Metropolitan University ManchesterM1 5GD United Kingdom Computer Science Department College of Computing and Informatics Saudi Electronic University Riyadh11673 Saudi Arabia

ISBN: (纸本)9781450387347

The importance of drone use is increasing in all fields due to several characteristics and advantages they provide, such as saving lives, quality imaging, and being easily controllable. In addition, Unmanned Aerial Vehicle (UAV) prices are going to decrease, this has contributed greatly to an increase in demand for them. However, many challenges face the widespread use of UAVs. One of the most important challenges is his vulnerability to hacking. This paper presents a semi-decentralized collaboration model for the secure measurement of drone positions. The proposed model is based on choosing a leader for each specified period of time by a lightweight consensus algorithm. The leader gets his position using satellites, other drone team members are based on the leader's safe position to find their locations in a way that is immune to GPS spoofing. Our proposal study shows the extent of the security level it provides against spoofing attacks. © 2021 ACM.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

PollenNet: A novel architecture for high precision pollen grain classification through deep learning and explainable AI

引用

Heliyon 2024年第19期10卷 e38596页

作者： Shamrat, F M Javed Mehedi Idna Idris, Mohd Yamani Zhou, Xujuan Khalid, Majdi Sharmin, Sharmin Sharmin, Zeseya Ahmed, Kawsar Moni, Mohammad Ali Department of Computer System and Technology Universiti Malaya Kuala Lumpur 50603 Malaysia School of Business University of Southern Queensland Toowoomba Australia Department of Computer Science and Artificial Intelligence College of Computing Umm Al-Qura University Makkah 21955 Saudi Arabia School of Information Technology Faculty of Science Engineering and Built Environment Deakin University Australia Department of Electrical and Computer Engineering University of Saskatchewan 57 Campus Drive Saskatoon S7N 5A9 SK Canada Group of Bio-photomatiχ Information and Communication Technology Mawlana Bhashani Science and Technology University Santosh Tangail 1902 Bangladesh Health Informatics Research Lab Department of Computer Science and Engineering Daffodil International University Daffodil Smart City (DSC) Birulia Savar Dhaka 1216 Bangladesh AI & Digital Health Technology Artificial Intelligence & Cyber Future Institute Charles Stuart University Bathurst 2795 NSW Australia AI & Digital Health Technology Rural Health Research Institute Charles Stuart University Orange 2800 NSW Australia

Pollen grains play a critical role in environmental, agricultural, and allergy research despite their tiny dimensions. The accurate classification of pollen grains remains a significant challenge, mainly attributable to their intricate structures and the extensive diversity of species. Traditional methods often lack accuracy and effectiveness, prompting the need for advanced solutions. This study introduces a novel deep learning framework, PollenNet, designed to tackle the intricate challenge of pollen grain image classification. The efficiency of PollenNet is thoroughly evaluated through stratified 5-fold cross-validation, comparing it with cutting-edge methods to demonstrate its superior performance. A comprehensive data preparation phase is conducted, including removing duplicates and low-quality images, applying Non-local Means Denoising for noise reduction, and Gamma correction to adjust image brightness. Furthermore, Explainable AI (XAI) is utilized to enhance the interpretability of the model, while Receiver Operating Characteristic (ROC) curve analysis serves as a quantitative method for evaluating the model's capabilities. PollenNet demonstrates superior performance when compared to existing models, with an accuracy of 98.45 %, precision of 98.20 %, specificity of 98.40 %, recall of 98.30 %, and f1-score of 98.25 %. The model also maintains low Mean Squared Error (0.03) and Mean Absolute Error (0.02) rates. The ROC curve analysis, the low False Positive Rate (0.016), and the False Negative Rate (0.017) highlight the reliability and dependability of the model. This study significantly improves the efficacy of classifying pollen grains, indicating an important advancement in the application of deep learning for ecological research. © 2024 The Authors

关键词： Deep learning Explainable AI Image processing Pollen grain classification PollenNet model

来源：评论

学校读者我要写书评

暂无评论

On Algorithmic Descriptions and Software Implementations for Multi-objective Optimisation: A Comparative Study

引用

SN computer science 2020年第5期1卷 1-23页

作者： Rostami, Shahin Neri, Ferrante Gyaurski, Kiril Data Science Lab Polyra Limited Bournemouth BH8 9JN United Kingdom Department of Computing and Informatics Bournemouth University Bournemouth BH12 5BB United Kingdom COL Laboratory School of Computer Science University of Nottingham Nottingham NG8 1BB United Kingdom

Multi-objective optimisation is a prominent subfield of optimisation with high relevance in real-world problems, such as engineering design. Over the past 2 decades, a multitude of heuristic algorithms for multi-objective optimisation have been introduced and some of them have become extremely popular. Some of the most promising and versatile algorithms have been implemented in software platforms. This article experimentally investigates the process of interpreting and implementing algorithms by examining multiple popular implementations of three well-known algorithms for multi-objective optimisation. We observed that official and broadly employed software platforms interpreted and thus implemented the same heuristic search algorithm differently. These different interpretations affect the algorithmic structure as well as the software implementation. Numerical results show that these differences cause statistically significant differences in performance. © 2020, The Author(s).

关键词： Evolutionary algorithms Multi-objective optimisation Optimisation software platforms

来源：评论

学校读者我要写书评

暂无评论

A Survey on Deep Learning Technique for Video Segmentation

arXiv

引用

arXiv 2021年

作者： Zhou, Tianfei Porikli, Fatih Crandall, David J. Van Gool, Luc Wang, Wenguan ETH Zurich Switzerland The School of Computer Science Australian National University Australia The Luddy School of Informatics Computing and Engineering Indiana University United States ReLER Lab Australian Artificial Intelligence Institute University of Technology Sydney Australia

Video segmentation-partitioning video frames into multiple segments or objects-plays a critical role in a broad range of practical applications, from enhancing visual effects in movie, to understanding scenes in autonomous driving, to creating virtual background in video conferencing. Recently, with the renaissance of connectionism in computer vision, there has been an influx of deep learning based approaches for video segmentation that have delivered compelling performance. In this survey, we comprehensively review two basic lines of research - generic object segmentation (of unknown categories) in videos, and video semantic segmentation - by introducing their respective task settings, background concepts, perceived need, development history, and main challenges. We also offer a detailed overview of representative literature on both methods and datasets. We further benchmark the reviewed methods on several well-known datasets. Finally, we point out open issues in this field, and suggest opportunities for further research. We also provide a public website to continuously track developments in this fast advancing field: https://***/tfzhou/VS-Survey. Copyright © 2021, The Authors. All rights reserved.

关键词： Video conferencing

来源：评论

学校读者我要写书评

暂无评论

Towards Unified Token Learning for Vision-Language Tracking

arXiv

引用

arXiv 2023年

作者： Zheng, Yaozong Zhong, Bineng Liang, Qihua Li, Guorong Ji, Rongrong Li, Xianxian The Key Laboratory of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guilin541004 China The Guangxi Key Laboratory of Multi-Source Information Mining and Security Guangxi Normal University Guilin541004 China The School of Computer Science and Technology Key Laboratory of Big Data Mining and Knowledge Management University of Chinese Academy of Sciences Beijing100049 China Media Analytics and Computing Lab Department of Artificial Intelligence School of Informatics Xiamen University 361005 China

In this paper, we present a simple, flexible and effective vision-language (VL) tracking pipeline, termed MMTrack, which casts VL tracking as a token generation task. Traditional paradigms address VL tracking task indirectly with sophisticated prior designs, making them over-specialize on the features of specific architectures or mechanisms. In contrast, our proposed framework serializes language description and bounding box into a sequence of discrete tokens. In this new design paradigm, all token queries are required to perceive the desired target and directly predict spatial coordinates of the target in an auto-regressive manner. The design without other prior modules avoids multiple sub-tasks learning and hand-designed loss functions, significantly reducing the complexity of VL tracking modeling and allowing our tracker to use a simple cross-entropy loss as unified optimization objective for VL tracking task. Extensive experiments on TNL2K, LaSOT, LaSOText and OTB99-Lang benchmarks show that our approach achieves promising results, compared to other state-of-the-arts. Copyright © 2023, The Authors. All rights reserved.

关键词： Modeling languages

来源：评论

学校读者我要写书评

暂无评论

Opponent Modelling using Policy Reconstruction for Multi-Objective Normal Form Games

Opponent Modelling using Policy Reconstruction for Multi-Obj...

引用

Adaptive and Learning Agents Workshop, ALA 2020 at AAMAS 2020

作者： Zhang, Yijie Rădulescu, Roxana Mannion, Patrick Roijers, Diederik M. Nowé, Ann Informatics Institute Universiteit van Amsterdam Netherlands Artificial Intelligence Lab. Vrije Universiteit Brussel Belgium School of Computer Science National University of Ireland Galway Ireland Microsystems Technology HU Univ. of Appl. Sci. Utrecht Netherlands

In many multi-agent interactions in the real world, agents receive payoffs over multiple distinct criteria;i.e. the payoffs are multiobjective in nature. However, the same multi-objective payoff vector may lead to different utilities for each participant. Therefore, it is essential for an agent to learn about the behaviour of other agents in the system. In this work, we present the first study of the effects of such opponent modelling on multi-objective multiagent interactions with non-linear utilities. Specifically, we consider multi-objective normal form games with non-linear utility functions under the scalarised expected returns optimisation criterion. We contribute a novel actor-critic formulation to allow reinforcement learning of mixed strategies in this setting, along with an extension that incorporates opponent policy reconstruction using conditional action frequencies. Empirical results in five different MONFGs demonstrate that opponent modelling can drastically alter the learning dynamics in this setting. When equilibria are present opponent modelling can confer significant benefits on agents that implement it. However, when there are no Nash equilibria, opponent modelling can have adverse effects on utility, and has a neutral effect at best (after extensive hyper-parameter optimisation). © 2020 ALA 2020 - Adaptive and Learning Agents Workshop at AAMAS 2020. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Flip Learning: Weakly Supervised Erase to Segment Nodules in Breast Ultrasound

arXiv

引用

arXiv 2025年

作者： Huang, Yuhao Chang, Ao Dou, Haoran Tao, Xing Zhou, Xinrui Cao, Yan Huang, Ruobing Frangi, Alejandro F. Bao, Lingyun Yang, Xin Ni, Dong National-Regional Key Technology Engineering Laboratory for Medical Ultrasound School of Biomedical Engineering Shenzhen University Medical School Shenzhen University Shenzhen China Lab Shenzhen University Shenzhen China Marshall Laboratory of Biomedical Engineering Shenzhen University Shenzhen China School of Computing University of Leeds Leeds United Kingdom Shenzhen RayShape Medical Technology Co. Ltd Shenzhen China Division of Informatics Imaging and Data Science School of Health Sciences University of Manchester Manchester United Kingdom Department of Computer Science School of Engineering University of Manchester Manchester United Kingdom Department of Electrical Engineering Department of Cardiovascular Sciences KU Leuven Belgium Alan Turing Institute London United Kingdom NIHR Manchester Biomedical Research Centre Manchester Academic Health Science Centre Manchester United Kingdom Department of Ultrasound Affiliated Hangzhou First People’s Hospital School of Medicine Westlake University China School of Biomedical Engineering and Informatics Nanjing Medical University Nanjing China

Accurate segmentation of nodules in both 2D breast ultrasound (BUS) and 3D automated breast ultrasound (ABUS) is crucial for clinical diagnosis and treatment planning. Therefore, developing an automated system for nodule segmentation can enhance user independence and expedite clinical analysis. Unlike fully-supervised learning, weakly-supervised segmentation (WSS) can streamline the laborious and intricate annotation process. However, current WSS methods face challenges in achieving precise nodule segmentation, as many of them depend on inaccurate activation maps or inefficient pseudo-mask generation algorithms. In this study, we introduce a novel multi-agent reinforcement learning-based WSS framework called Flip Learning, which relies solely on 2D/3D boxes for accurate segmentation. Specifically, multiple agents are employed to erase the target from the box to facilitate classification tag flipping, with the erased region serving as the predicted segmentation mask. The key contributions of this research are as follows: 1) Adoption of a superpixel/supervoxel-based approach to encode the standardized environment, capturing boundary priors and expediting the learning process. 2) Introduction of three meticulously designed rewards, comprising a classification score reward and two intensity distribution rewards, to steer the agents’ erasing process precisely, thereby avoiding both under- and over-segmentation. 3) Implementation of a progressive curriculum learning strategy to enable agents to interact with the environment in a progressively challenging manner, thereby enhancing learning efficiency. Extensively validated on the large in-house BUS and ABUS datasets, our Flip Learning method outperforms state-of-the-art WSS methods and foundation models, and achieves comparable performance as fully-supervised learning algorithms. Copyright © 2025, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Brain multigraph prediction using topology-aware adversarial graph neural network

arXiv

引用

arXiv 2021年

作者： Bessadok, Alaa Mahjoub, Mohamed Ali Rekik, Islem BASIRA Lab Faculty of Computer and Informatics Istanbul Technical University Istanbul Turkey Higher Institute of Informatics and Communication Technologies University of Sousse Tunisia National Engineering School of Sousse University of Sousse LATIS- Laboratory of Advanced Technology and Intelligent Systems Sousse4023 Tunisia School of Science and Engineering Computing University of Dundee United Kingdom

Brain graphs (i.e, connectomes) constructed from medical scans such as magnetic resonance imaging (MRI) have become increasingly important tools to characterize the abnormal changes in the human brain. Due to the high acquisition cost and processing time of multimodal MRI, existing deep learning frameworks based on Generative Adversarial Network (GAN) focused on predicting the missing multimodal medical images from a few existing modalities. While brain graphs help better understand how a particular disorder can change the connectional facets of the brain, synthesizing a target brain multigraph (i.e, multiple brain graphs) from a single source brain graph is strikingly lacking. Additionally, existing graph generation works mainly learn one model for each target domain which limits their scalability in jointly predicting multiple target domains. Besides, while they consider the global topological scale of a graph (i.e., graph connectivity structure), they overlook the local topology at the node scale (e.g., how central a node is in the graph). To address these limitations, we introduce topology-aware graph GAN architecture (topoGAN), which jointly predicts multiple brain graphs from a single brain graph while preserving the topological structure of each target graph. Its three key innovations are: (i) designing a novel graph adversarial auto-encoder for predicting multiple brain graphs from a single one, (ii) clustering the encoded source graphs in order to handle the mode collapse issue of GAN and proposing a cluster-specific decoder, (iii) introducing a topological loss to force the prediction of topologically sound target brain graphs. The experimental results using five target domains demonstrated the outperformance of our method in brain multigraph prediction from a single graph in comparison with baseline approaches. © 2021, CC BY-NC-SA.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

Pareto-aware Neural Architecture Generation for Diverse Computational Budgets

arXiv

引用

arXiv 2022年

作者： Guo, Yong Chen, Yaofo Zheng, Yin Chen, Qi Zhao, Peilin Chen, Jian Huang, Junzhou Tan, Mingkui The School of Software Engineering South China University of Technology China Max Planck Institute for Informatics Germany The Weixin Group Tencent China The School of Computer Science The University of Adelaide Australia Tencent AI Lab Tencent China The Key Laboratory of Big Data and Intelligent Robot South China University of Technology Ministry of Education China The Pazhou Laboratory Guangzhou China

Designing feasible and effective architectures under diverse computational budgets, incurred by different applications/devices, is essential for deploying deep models in real-world applications. To achieve this goal, existing methods often perform an independent architecture search process for each target budget, which is very inefficient yet unnecessary. More critically, these independent search processes cannot share their learned knowledge (i.e., the distribution of good architectures) with each other and thus often result in limited search results. To address these issues, we propose a Pareto-aware Neural Architecture Generator (PNAG) which only needs to be trained once and dynamically produces the Pareto optimal architecture for any given budget via inference. To train our PNAG, we learn the whole Pareto frontier by jointly finding multiple Pareto optimal architectures under diverse budgets. Such a joint search algorithm not only greatly reduces the overall search cost but also improves the search results. Extensive experiments on three hardware platforms (i.e., mobile device, CPU, and GPU) show the superiority of our method over existing methods. Copyright © 2022, The Authors. All rights reserved.

关键词： Pareto principle

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：