检索结果-内蒙古大学图书馆

41st International Conference on machine learning, ICML 2024

作者： Papamarkou, Theodore Skoularidou, Maria Palla, Konstantina Aitchison, Laurence Arbel, Julyan Dunson, David Filippone, Maurizio Fortuin, Vincent Hennig, Philipp Hernández-Lobato, José Miguel Hubin, Aliaksandr Immer, Alexander Karaletsos, Theofanis Khan, Mohammad Emtiyaz Kristiadi, Agustinus Li, Yingzhen Mandt, Stephan Nemeth, Christopher Osborne, Michael A. Rudner, Tim G.J. Rügamer, David Teh, Yee Whye Welling, Max Wilson, Andrew Gordon Zhang, Ruqi Department of Mathematics The University of Manchester Manchester United Kingdom Eric and Wendy Schmidt Center Broad Institute of MIT and Harvard Cambridge United States Spotify London United Kingdom Computational Neuroscience Unit University of Bristol Bristol United Kingdom Centre Inria de l'Université Grenoble Alpes Grenoble France Department of Statistical Science Duke University United States Statistics Program KAUST Saudi Arabia Helmholtz AI Munich Germany Department of Computer Science Technical University of Munich Munich Germany Munich Center for Machine Learning Munich Germany Tübingen AI Center University of Tübingen Tübingen Germany Department of Engineering University of Cambridge Cambridge United Kingdom Department of Mathematics University of Oslo Oslo Norway Bioinformatics and Applied Statistics Norwegian University of Life Sciences Ås Norway Department of Computer Science ETH Zurich Switzerland Chan Zuckerberg Initiative CA United States Center for Advanced Intelligence Project RIKEN Tokyo Japan Vector Institute Toronto Canada Department of Computing Imperial College London London United Kingdom Department of Computer Science UC Irvine Irvine United States Department of Mathematics and Statistics Lancaster University Lancaster United Kingdom Department of Engineering Science University of Oxford Oxford United Kingdom Center for Data Science New York University New York United States Department of Statistics LMU Munich Munich Germany DeepMind London United Kingdom Department of Statistics University of Oxford Oxford United Kingdom Informatics Institute University of Amsterdam Amsterdam Netherlands Courant Institute of Mathematical Sciences Center for Data Science Computer Science Department New York University New York United States Department of Computer Science Purdue University West Lafayette United States

In the current landscape of deep learning research, there is a predominant emphasis on achieving high predictive accuracy in supervised tasks involving large image and language datasets. However, a broader perspective reveals a multitude of overlooked metrics, tasks, and data types, such as uncertainty, active and continual learning, and scientific data, that demand attention. Bayesian deep learning (BDL) constitutes a promising avenue, offering advantages across these diverse settings. This paper posits that BDL can elevate the capabilities of deep learning. It revisits the strengths of BDL, acknowledges existing challenges, and highlights some exciting research avenues aimed at addressing these obstacles. Looking ahead, the discussion focuses on possible ways to combine large-scale foundation models with BDL to unlock their full potential. Copyright 2024 by the author(s)

关键词： Contrastive learning

来源：评论

学校读者我要写书评

暂无评论

The dark balance: quantifying the inner halo response to active galactic nuclei feedback in galaxies

arXiv

引用

arXiv 2024年

作者： Arora, Nikhil Courteau, Stéphane Macciò, Andrea V. Cho, Changhyun Patel, Raj Stone, Connor New York University Abu Dhabi PO Box 129188 Abu Dhabi United Arab Emirates New York University Abu Dhabi Abu Dhabi PO Box 129188 Abu Dhabi United Arab Emirates Department of Physics Engineering Physics & Astronomy Queen’s University KingstonONK7L 3N6 Canada Max-Planck-Institut für Astronomie Königstuhl 17 HeidelbergD-69117 Germany Department of Physics Université de Montréal MontréalQC Canada Mila - Québec Artificial Intelligence Institute MontréalQC Canada Ciela - Montréal Institute for Astrophysical Data Analysis and Machine Learning MontréalQC Canada

This paper presents a study of the impact of supermassive black hole (SMBH) feedback on dark matter (DM) halos in numerical NIHAO simulations of galaxies. In particular, the amount of DM displaced via active galactic nuclei (AGN) feedback and the physical scale over which AGN feedback affects the DM halo are quantified by comparing NIHAO simulations with and without AGN feedback. NIHAO galaxies with log(M∗/M☉) ≥ 10.0 show a growing central DM suppression of 0.2 dex (∼40 per cent) from z = 1.5 to the present relative to noAGN feedback simulations. The growth of the DM suppression is related to the mass evolution of the SMBH and the gas mass in the central regions. For the most massive NIHAO galaxies log(M∗/M☉) > 10.5, partially affected by numerical resolution, the central DM suppression peaks at z = 0.5, after which halo contraction overpowers AGN feedback due a shortage of gas and, thus, SMBH growth. The spatial scale, or "sphere of influence," over which AGN feedback affects the DM distribution decreases as a function of time for MW-mass galaxies (from ∼16 kpc at z = 1.5 to ∼7.8 kpc at z = 0) as a result of halo contraction due to stellar growth. For the most massive NIHAO galaxies, the size of the sphere of influence remains constant (∼16 kpc) for z > 0.5 owing to the balance between AGN feedback and halo contraction. © 2024, CC BY.

关键词： Active Galactic Nuclei

来源：评论

学校读者我要写书评

暂无评论

Position: Bayesian deep learning is needed in the age of large-scale AI 24

Position: Bayesian deep learning is needed in the age of lar...

引用

Proceedings of the 41st International Conference on machine learning

作者： Theodore Papamarkou Maria Skoularidou Konstantina Palla Laurence Aitchison Julyan Arbel David Dunson Maurizio Filippone Vincent Fortuin Philipp Hennig José Miguel Hernández-Lobato Aliaksandr Hubin Alexander Immer Theofanis Karaletsos Mohammad Emtiyaz Khan Agustinus Kristiadi Yingzhen Li Stephan Mandt Christopher Nemeth Michael A. Osborne Tim G. J. Rudner David Rügamer Yee Whye Teh Max Welling Andrew Gordon Wilson Ruqi Zhang Department of Mathematics The University of Manchester Manchester UK Eric and Wendy Schmidt Center Broad Institute of MIT and Harvard Cambridge Spotify London UK Computational Neuroscience Unit University of Bristol Bristol UK Centre Inria de l'Université Grenoble Alpes Grenoble France Department of Statistical Science Duke University Statistics Program KAUST Saudi Arabia Helmholtz AI Munich Germany and Department of Computer Science Technical University of Munich Munich Germany and Munich Center for Machine Learning Munich Germany Tübingen AI Center University of Tübingen Tübingen Germany Department of Engineering University of Cambridge Cambridge UK Department of Mathematics University of Oslo Oslo Norway and Bioinformatics and Applied Statistics Norwegian University of Life Sciences Ås Norway Department of Computer Science ETH Zurich Switzerland Chan Zuckerberg Initiative California Center for Advanced Intelligence Project RIKEN Tokyo Japan Vector Institute Toronto Canada Department of Computing Imperial College London London UK Department of Computer Science UC Irvine Irvine Department of Mathematics and Statistics Lancaster University Lancaster UK Department of Engineering Science University of Oxford Oxford UK Center for Data Science New York University New York Munich Center for Machine Learning Munich Germany and Department of Statistics LMU Munich Munich Germany DeepMind London UK and Department of Statistics University of Oxford Oxford UK Informatics Institute University of Amsterdam Amsterdam Netherlands Courant Institute of Mathematical Sciences and Center for Data Science Computer Science Department New York University New York Department of Computer Science Purdue University West Lafayette

关键词：

来源：评论

学校读者我要写书评

暂无评论

Survey on reliable deep learning-based person re-identification models: Are we there yet?

arXiv

引用

arXiv 2020年

作者： Lavi, Bahram Ullah, Ihsan Fatan, Mehdi Rocha, Anderson Campinas São Paulo Brazil Data Mining & Machine Learning Group Discipline of IT National University of Ireland Galway Ireland Department of Computer Engineering and Mathematics University Rovira i Virgili Tarragona Spain

Intelligent video-surveillance (IVS) is currently an active research field in computer vision and machine learning and provides useful tools for surveillance operators and forensic video investigators. Person re-identification (PReID) is one of the most critical problems in IVS, and it consists of recognizing whether or not an individual has already been observed over a camera in a network. Solutions to PReID have myriad applications including retrieval of video-sequences showing an individual of interest or even pedestrian tracking over multiple camera views. Different techniques have been proposed to increase the performance of PReID in the literature, and more recently researchers utilized deep neural networks (DNNs) given their compelling performance on similar vision problems and fast execution at test time. Given the importance and wide range of applications of re-identification solutions, our objective herein is to discuss the work carried out in the area and come up with a survey of state-of-the-art DNN models being used for this task. We present descriptions of each model along with their evaluation on a set of benchmark datasets. Finally, we show a detailed comparison among these models, which are followed by some discussions on their limitations that can work as guidelines for future research. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Impact of Distributed Training on Mask R-CNN Model Performance for Image Segmentation

Impact of Distributed Training on Mask R-CNN Model Performan...

引用

Emerging Trends in Information Technology and engineering (ic-ETITE), Conference on

作者： Mercy Prasanna Ranjit Gopinath Ganapathy Ranjit Frederick Manuel AI & Machine Learning Microsoft Corporation India Ltd Bangalore India School of Computer Science and Engineering Bharathidasan University Trichy India Data Analytics & AI ITC Infotech India Ltd Bangalore India

ISBN: (数字)9781728141428

ISBN: (纸本)9781728141435

The paper compares and discusses the impact of distributed deep learning training using the Horovod framework on the performance metrics of image segmentation model trained using the Mask R-CNN (Region-based Convolutional Neural Network) architecture in comparison with the baseline metrics obtained from running the training on a single node. Image segmentation is a complex problem in comparison with image classification and the fluctuations introduced due to the distributed gradient computations while running the training distributed is less pronounced on simpler problems like image classification while it is more pronounced for image segmentation where we measure the performance at pixel level. It is important to know how the latest algorithms and distribution frameworks perform when training the model on distributed compute with parallel gradient calculations, adjusted learning rates and averaged neural network weight updates. The paper also aimed to understand if the effective batch size per training iteration while performing the training distributed did not negatively impact the ability of the model to generalize when increasing the batch size as indicated in the previous studies. The distributed training with Horovod was performed using the Azure machine learning service on scalable cloud compute cluster. The aim of the study was not comparison in-terms of the execution time which has been well established on previous studies but on understanding the impact on the quality of the predictions measured with standard validation metrics for image segmentation using the ISIC (International Skin Imaging Collaboration) 2018 Skin Lesion image dataset.

关键词： Image Segmentation Distributed training Horovod Deep learning Mask-RCNN image segmentation Training Functional training Image classification Distribute execution time Performance metrics Masks

来源：评论

学校读者我要写书评

暂无评论

Brain Imaging Generation with Latent Diffusion Models

arXiv

引用

arXiv 2022年

作者： Pinaya, Walter H.L. Tudosiu, Petru-Daniel Dafflon, Jessica Da Costa, Pedro F. Fernandez, Virginia Nachev, Parashkev Ourselin, Sebastien Cardoso, M. Jorge Department of Biomedical Engineering School of Biomedical Engineering & Imaging Sciences King’s College London United Kingdom Data Science and Sharing Team Functional Magnetic Resonance Imaging Facility National Institute of Mental Health BethesdaMD20892 United States Machine Learning Team Functional Magnetic Resonance Imaging Facility National Institute of Mental Health BethesdaMD20892 United States Institute of Psychiatry Psychology & Neuroscience King’s College London United Kingdom Centre for Brain and Cognitive Development Birkbeck College United Kingdom Institute of Neurology University College London United Kingdom

Deep neural networks have brought remarkable breakthroughs in medical image analysis. However, due to their data-hungry nature, the modest dataset sizes in medical imaging projects might be hindering their full potential. Generating synthetic data provides a promising alternative, allowing to complement training datasets and conducting medical image research at a larger scale. Diffusion models recently have caught the attention of the computer vision community by producing photorealistic synthetic images. In this study, we explore using Latent Diffusion Models to generate synthetic images from high-resolution 3D brain images. We used T1w MRI images from the UK Biobank dataset (N=31,740) to train our models to learn about the probabilistic distribution of brain images, conditioned on covariables, such as age, sex, and brain structure volumes. We found that our models created realistic data, and we could use the conditioning variables to control the data generation effectively. Besides that, we created a synthetic dataset with 100,000 brain images and made it openly available to the scientific community. © 2022, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Adaptive distributed honeypot detection network for enhanced cybersecurity against DoS and DDoS attacks

Results in Engineering

引用

Results in engineering 2025年 26卷

作者： V. Selva Kumar K.R. Mohan Raj S. Gopalakrishnan G. Vennila D. Dhinakaran P. Kavitha Department of Computer Science and Engineering P.S.R. Engineering College Sivakasi India Department of Information Technology Velammal Engineering College Chennai India Department of Computer Science & Engineering (Data Science) Madanapalle Institute of Technology & Science Andhra Pradesh India Department of Artificial Intelligence and Machine Learning School of Computing Mohan Babu University Tirupati India Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India Department of Computer Science and Engineering R.M.K. Engineering college Chennai India

The increasing prevalence and sophistication of Denial of Service (DoS) and Distributed Denial of Service (DDoS) attacks present significant challenges in ensuring the security and stability of modern networked systems. These attacks, characterized by their ability to disrupt services and compromise resources, require innovative and robust detection mechanisms to safeguard highly interactive environments such as honeypot systems. Traditional detection techniques often fall short in addressing the complexities posed by dynamic traffic patterns, diverse attack types, and real-time processing demands. This study introduces the Adaptive Distributed Honeypot Detection Network (ADHDN), a novel framework that leverages deep learning and probabilistic modeling to address the limitations of existing solutions. ADHDN employs a combination of Deep Generative Adversarial Networks (DGANs) and Discrete Hidden Markov Models (DHMMs) to achieve superior detection precision across various DoS attack types, including application-level, protocol-level, and data volume attacks. Implemented in a highly interactive honeypot environment with distributed server and virtual machine configurations, ADHDN demonstrates remarkable adaptability and resilience. Performance evaluation using the IoTID20 dataset reveals that ADHDN consistently outperforms contemporary models, such as RBMD, BNDH, and AHDL. ADHDN achieves a true positive rate of 99.7% for protocol-level attacks, 99.4% for application-level attacks, and 97.5% for data volume attacks under low attack volumes, maintaining robust performance even as attack intensity scales. These results underscore ADHDN’s potential to redefine DoS detection in dynamic and high-interaction environments, offering a scalable and efficient solution to contemporary cybersecurity challenges.

关键词： Denial of service Distributed denial of service Intrusion detection systems Generative adversarial networks Real-time attack detection Deep learning

来源：评论

学校读者我要写书评

暂无评论

On Convergence of Federated Averaging Langevin Dynamics

arXiv

引用

arXiv 2021年

作者： Deng, Wei Zhang, Qian Ma, Yi-An Song, Zhao Lin, Guang Machine Learning Research Morgan Stanley NY United States Department of Statistics Purdue University West LafayetteIN United States Haliciog˜lu Data Science Institute University of California La Jolla San DiegoCA United States Adobe Research San JoseCA United States Department of Mathematics School of Mechanical Engineering Purdue University United States

We propose a federated averaging Langevin algorithm (FA-LD) for uncertainty quantification and mean predictions with distributed clients. In particular, we generalize beyond normal posterior distributions and consider a general class of models. We develop theoretical guarantees for FA-LD for strongly log-concave distributions with non-i.i.d data and study how the injected noise and the stochastic-gradient noise, the heterogeneity of data, and the varying learning rates affect the convergence. Such an analysis sheds light on the optimal choice of local updates to minimize the communication cost. Important to our approach is that the communication efficiency does not deteriorate with the injected noise in the Langevin algorithms. In addition, we examine in our FA-LD algorithm both independent and correlated noise used over different clients. We observe there is a trade-off between the pairs among communication, accuracy, and data privacy. As local devices may become inactive in federated networks, we also show convergence results based on different averaging schemes where only partial device updates are available. In such a case, we discover an additional bias that does not decay to zero. © 2021, CC BY.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Comprehensive empirical evaluation of deep learning approaches for session-based recommendation in e-commerce

arXiv

引用

arXiv 2020年

作者： Maher, Mohamed Ngoy, Perseverance Munga Rebriks, Aleksandrs Ozcinar, Cagri Cuevas, Josue Sanagavarapu, Rajasekhar Anbarjafari, Gholamreza University of Tartu Tartu Estonia iCV Lab University of Tartu Tartu Estonia Faculty of Engineering Hasan Kalyoncu University Gaziantep Turkey Rakuten Inc. Big Data Department Machine Learning Group Tokyo Japan

Boosting sales of e-commerce services is guaranteed once users find more matching items to their interests in a short time. Consequently, recommendation systems have become a crucial part of any successful e-commerce services. Although various recommendation techniques could be used in e-commerce, a considerable amount of attention has been drawn to session-based recommendation systems during the recent few years. This growing interest is due to the security concerns in collecting personalized user behavior data, especially after the recent general data protection regulations 1. In this work, we present a comprehensive evaluation of the state-of-the-art deep learning approaches used in the session-based recommendation. In session-based recommendation, a recommendation system counts on the sequence of events made by a user within the same session to predict and endorse other items that are more likely to correlate with his/her preferences. Our extensive experiments investigate baseline techniques (e.g., nearest neighbors and pattern mining algorithms) and deep learning approaches (e.g., recurrent neural networks, graph neural networks, and attention-based networks). Our evaluations show that advanced neural-based models and session-based nearest neighbor algorithms outperform the baseline techniques in most of the scenarios. However, we found that these models suffer more in case of long sessions when there exists drift in user interests, and when there is no enough data to model different items correctly during training. Our study suggests that using hybrid models of different approaches combined with baseline algorithms could lead to substantial results in session-based recommendations based on dataset characteristics. We also discuss the drawbacks of current session-based recommendation algorithms and further open research directions in this field. Copyright © 2020, The Authors. All rights reserved.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Accurately predicting anticancer peptide using an ensemble of heterogeneously trained classifiers

引用

Informatics in Medicine Unlocked 2023年 42卷

作者： Azim, Sayed Mehedi Sabab, Noor Hossain Nuri Noshadi, Iman Alinejad-Rokny, Hamid Sharma, Alok Shatabda, Swakkhar Dehzangi, Iman Center for Computational and Integrative Biology Rutgers University Camden 08102 NJ United States Department of Computer Science and Engineering United International University Plot 2 United City Madani Avenue BaddaDhaka 1212 Bangladesh Department of Bioengineering University of California Riverside 92507 CA United States BioMedical Machine Learning Lab The Graduate School of Biomedical Engineering The University of New South Wales (UNSW Sydney) Sydney NSW 2052 Australia UNSW Data Science Hub UNSW Sydney Sydney NSW 2052 Australia Health Data Analytics Program AI-enabled Processes Research Centre Macquarie University Sydney 2109 Australia Institute for Integrated and Intelligent Systems Griffith University Brisbane Australia Laboratory for Medical Science Mathematics RIKEN Center for Integrative Medical Sciences Yokohama 230-0045 Japan Department of Computer Science Rutgers University Camden 08102 NJ United States

The use of therapeutic peptides for the treatment of cancer has received tremendous attention in recent years. Anticancer peptides (ACPs) are considered new anticancer drugs which have several advantages over chemistry-based drugs including high specificity, strong tumor penetration capacity, and low toxicity level for normal cells. Due to the rise of experimentally verified bioactive peptides, several in silico approaches became imperative for the investigation of the characteristics of ACPs. In this paper, we proposed a new machine learning tool named iACP-RF that uses a combination of several sequence-based features and an ensemble of three heterogeneously trained Random Forest classifiers to accurately predict anticancer peptides. Experimental results show that our proposed model achieves an accuracy of 75.9% which outperforms other state-of-the-art methods by a significant margin. We also achieve 0.52, 75.6%, and 76.2% in terms of Matthews Correlation Coefficient (MCC), Sensitivity, and Specificity, respectively. iACP-RF as a standalone tool and its source code are publicly available at: https://***/MLBC-lab/iACP-RF. © 2023 The Authors

关键词： Anticancer peptides Ensemble learning Feature extraction Heterogeneous classifiers machine learning Random Forest

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：