检索结果-内蒙古大学图书馆

Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI 41

学校读者我要写书评

暂无评论

Position: Bayesian Deep Learning is Needed in the Age of Lar...

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

Clinically Interpretable Machine Learning Models for Early Prediction of Mortality in Older Patients with Multiple Organ Dysfunction Syndrome: An International Multicenter Retrospective Study

学校读者我要写书评

暂无评论

Journals of Gerontology - Series A Biological sciences and Medical sciences 2023年第4期78卷 718-726页

作者： Liu, Xiaoli DuMontier, Clark Hu, Pan Liu, Chao Yeung, Wesley Mao, Zhi Ho, Vanda Thoral, Patrick J. Kuo, Po-Chih Hu, Jie Li, Deyu Cao, Desen Mark, Roger G. Zhou, FeiHu Zhang, Zhengbo Celi, Leo Anthony Key Laboratory for Biomechanics and Mechanobiology of Ministry of Education Beijing Advanced Innovation Center for Biomedical Engineering School of Biological Science and Medical Engineering Beihang University Beijing China Laboratory for Computational Physiology Institute for Medical Engineering and Science Massachusetts Institute of Technology Cambridge MA United States Center for Artificial Intelligence in Medicine General Hospital of PLA Beijing China New England Geriatric Research Education and Clinical Center VA Boston Healthcare System Boston MA United States Division of Aging Brigham and Women's Hospital Boston MA United States Department of Anesthesiology 920 Hospital of Joint Logistic Support Force of Chinese PLA Kunming Yunnan China Department of Critical Care Medicine First Medical Center General Hospital of PLA Beijing China Department of Medicine National University Hospital Singapore Division of Geriatric Medicine Department of Medicine National University Hospital Singapore Department of Intensive Care Medicine Amsterdam Netherlands Department of Computer Science National Tsing Hua University Hsinchu Taiwan Department of Biomedical Engineering General Hospital of PLA Beijing China Elderly Center General Hospital of PLA Beijing China Department of Medicine Beth Israel Deaconess Medical Center Boston MA United States Department of Biostatistics Harvard T.H. Chan School of Public Health Boston MA United States

BACKGROUND: Multiple organ dysfunction syndrome (MODS) is associated with a high risk of mortality among older patients. Current severity scores are limited in their ability to assist clinicians with triage and management decisions. We aim to develop mortality prediction models for older patients with MODS admitted to the ICU. METHODS: The study analyzed older patients from 197 hospitals in the United States and 1 hospital in the Netherlands. The cohort was divided into the young-old (65-80 years) and old-old (≥80 years), which were separately used to develop and evaluate models including internal, external, and temporal validation. Demographic characteristics, comorbidities, vital signs, laboratory measurements, and treatments were used as predictors. We used the XGBoost algorithm to train models, and the SHapley Additive exPlanations (SHAP) method to interpret predictions. RESULTS: Thirty-four thousand four hundred and ninety-seven young-old (11.3% mortality) and 21 330 old-old (15.7% mortality) patients were analyzed. Discrimination AUROC of internal validation models in 9 046 U.S. patients was as follows: 0.87 and 0.82, respectively;discrimination of external validation models in 1 905 EUR patients was as follows: 0.86 and 0.85, respectively;and discrimination of temporal validation models in 8 690 U.S. patients: 0.85 and 0.78, respectively. These models outperformed standard clinical scores like Sequential Organ Failure Assessment and Acute Physiology Score III. The Glasgow Coma Scale, Charlson Comorbidity Index, and Code Status emerged as top predictors of mortality. CONCLUSIONS: Our models integrate data spanning physiologic and geriatric-relevant variables that outperform existing scores used in older adults with MODS, which represents a proof of concept of how machine learning can streamline data analysis for busy ICU clinicians to potentially optimize prognostication and decision making. © The Author(s) 2022. Published by Oxford University Press on behalf

关键词： International multicenter Interpretable models Machine learning Mortality Multiple organ dysfunction syndrome

Integration of Droplet Microfluidic Tools for Single-cell Functional Metagenomics:An engineering Head Start

学校读者我要写书评

暂无评论

Genomics, Proteomics & Bioinformatics 2021年第3期19卷 504-518页

作者： David Conchouso Amani Al-Ma’abadi Hayedeh Behzad Mohammed Alarawi Masahito Hosokawa Yohei Nishikawa Haruko Takeyama Katsuhiko Mineta Takashi Gojobori Department of Industrial and Mechanical Engineering Universidad de las Américas PueblaPuebla 72810Mexico Computational Bioscience Research Center King Abdullah University of Science and TechnologyThuwal 23955-6900Saudi Arabia Biological and Environmental Sciences and Engineering Division King Abdullah University of Science and TechnologyThuwal 23955-6900Saudi Arabia Research Organization for Nano&Life Innovation Waseda UniversityTokyo 162-0041Japan Department of Life Science and Medical Bioscience Waseda UniversityTokyo 162-8480Japan Institute for Advanced Research of Biosystem Dynamics Waseda Research Institute for Science and EngineeringWaseda UniversityTokyo 169-8555Japan Computational Bio Big-Data Open Innovation Laboratory AIST-Waseda UniversityTokyo 169–0072Japan Computer Electricaland Mathematical Sciences and Engineering DivisionKing Abdullah University of Science and TechnologyThuwal 23955-6900Saudi Arabia

Droplet microfluidic techniques have shown promising outcome to study single cells at high ***,their adoption in laboratories studying“-omics”sciences is still irrelevant due to the complex and multidisciplinary nature of the *** facilitate their use,here we provide engineering details and organized protocols for integrating three droplet-based microfluidic technologies into the metagenomic pipeline to enable functional screening of bioproducts at high ***,a device encapsulating single cells in droplets at a rate of~250 Hz is described considering droplet size and cell ***,we expand on previously reported fluorescence-activated droplet sorting systems to integrate the use of 4 independent fluorescence-exciting lasers(i.e.,405,488,561,and 637 nm)in a single platform to make it compatible with different fluorescence-emitting *** this sorter,both hardware and software are provided and optimized for effortlessly sorting droplets at 60 ***,a passive droplet merger is also integrated into our pipeline to enable adding new reagents to already-made droplets at a rate of 200 ***,we provide an optimized recipe for manufacturing these chips using silicon dry-etching *** of the overall integration and the technical details presented here,our approach allows biologists to quickly use microfluidic technologies and achieve both single-cell resolution and high-throughput capability(>50,000 cells/day)for mining and bioprospecting metagenomic data.

关键词： Droplet microfluidics Single cell Metagenomics Droplet sorter Biotechnology

Classification of Breast Thermal Images into Healthy/Cancer Group Using Pre-Trained Deep Learning Schemes

学校读者我要写书评

暂无评论

Classification of Breast Thermal Images into Healthy/Cancer ...

2022 International Conference on Machine Learning and data engineering, ICMLDE 2022

作者： Kadry, Seifedine Crespo, Rubén González Herrera-Viedma, Enrique Krishnamoorthy, Sujatha Rajinikanth, Venkatesan Faculty of Applied Computing and Technology Noroff University College Kristiansand94612 Norway Computer Science Department School of Engineering and Technology Universidad Internacional de la Rioja Andalusia26006 Spain Research Institute in Data Science and Computational Intelligence University of Granada Granada Spain Zhejiang Bioinformatics International Science and Technology Cooperation Center Wenzhou-Kean University Zhejiang Province China Wenzhou Municipal Key Lab of Applied Biomedical and Biopharmaceutical Informatics Wenzhou-Kean University Zhejiang Province China Department of Computer Science and Engineering Saveetha School of Engineering SIMATS Tamil Nadu Chennai602105 India

In the women's community, Breast Cancer (BC) is a severe disease. The World Health Organization reported in 2020 that 2.26 million deaths occur due to BC. BC is curable if detected early. Since thermal imaging is non-invasive and supports disease detection, it is commonly used in clinics. Compared to other methods, it keeps BC early and accurate. The proposed work aims to evaluate the performance of the Pretrained Deep-Learning Methods (PDLM) in detecting BC using the thermal images collected from the benchmark dataset. It includes the following stages: primary image processing, deep feature mining, handcrafted feature mining, feature optimization using Firefly-Algorithm (FA), classification and validation. Visual Lab thermal images were used in the study. The investigational outcome of this study authenticates that the VGG16, along with the DT, provides better detection accuracy (95.5%) compared to other classifiers used in this study. To justify the significance of the implemented technique, the proposed work not only improved accuracy, but also improved precision, sensitivity, specificity, and F1-Scores. © 2023 The Authors. Published by Elsevier B.V.

关键词： Classification (of information)

Rotation-Adaptive Point Cloud Domain Generalization via Intricate Orientation Learning

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Liu, Bangzhen Zheng, Chenxi Xu, Xuemiao Xu, Cheng Zhang, Huaidong He, Shengfeng South China University of Technology Guangzhou China Guangdong Engineering Center for Large Model and GenAI Technology The State Key Laboratory of Subtropical Building and Urban Science The Ministry of Education Key Laboratory of Big Data and Intelligent Robot The Guangdong Provincial Key Lab of Computational Intelligence and Cyberspace Information China Singapore Management University Singapore

The vulnerability of 3D point cloud analysis to unpredictable rotations poses an open yet challenging problem: orientation-aware 3D domain generalization. Cross-domain robustness and adaptability of 3D representations are crucial but not easily achieved through rotation augmentation. Motivated by the inherent advantages of intricate orientations in enhancing generalizability, we propose an innovative rotation-adaptive domain generalization framework for 3D point cloud analysis. Our approach aims to alleviate orientational shifts by leveraging intricate samples in an iterative learning process. Specifically, we identify the most challenging rotation for each point cloud and construct an intricate orientation set by optimizing intricate orientations. Subsequently, we employ an orientation-aware contrastive learning framework that incorporates an orientation consistency loss and a margin separation loss, enabling effective learning of categorically discriminative and generalizable features with rotation consistency. Extensive experiments and ablations conducted on 3D cross-domain benchmarks firmly establish the state-of-the-art performance of our proposed approach in the context of orientation-aware 3D domain generalization. © 2025, CC BY-NC-SA.

关键词： Contrastive Learning

THE BLESSINGS OF MULTIPLE TREATMENTS AND OUTCOMES IN TREATMENT EFFECT ESTIMATION

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wu, Yong Liu, Mingzhou Yan, Jing Fu, Yanwei Wang, Shouyan Wang, Yizhou Sun, Xinwei Institute of Science and Technology for Brain-Inspired Intelligence Fudan University China Computer Science Department Peking University China School of Data Science Fudan University China Key Laboratory of Computational Neuroscience Brain-Inspired Intelligence China MOE Frontiers Center for Brain Science Fudan University China Zhangjiang Fudan International Innovation Center China Engineering Research Center of AI & Robotics Ministry of Education Fudan University China

Assessing causal effects in the presence of unobserved confounding is a challenging problem. Existing studies leveraged proxy variables or multiple treatments to adjust for the confounding bias. In particular, the latter approach attributes the impact on a single outcome to multiple treatments, allowing estimating latent variables for confounding control. Nevertheless, these methods primarily focus on a single outcome, whereas in many real-world scenarios, there is greater interest in studying the effects on multiple outcomes. Besides, these outcomes are often coupled with multiple treatments. Examples include the intensive care unit (ICU), where health providers evaluate the effectiveness of therapies on multiple health indicators. To accommodate these scenarios, we consider a new setting dubbed as multiple treatments and multiple outcomes. We then show that parallel studies of multiple outcomes involved in this setting can assist each other in causal identification, in the sense that we can exploit other treatments and outcomes as proxies for each treatment effect under study. We proceed with a causal discovery method that can effectively identify such proxies for causal estimation. The utility of our method is demonstrated in synthetic data and sepsis disease. Copyright © 2023, The Authors. All rights reserved.

关键词： intensive care units

A S I N G L E I M AG E D E E P L E A R N I N G A P P ROAC H TO R E S TO R AT I O N O F C O R RU P T E D R E M OT E S E N S I N G P RO D U C T S

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Petrovskaia, Anna Jana, Raghavendra B. Oseledets, Ivan V. Center for Computational and Data-Intensive Science and Engineering Skolkovo Institute of Science and Technology Moscow121205 Russia

Remote sensing images are used for a variety of analyses, from agricultural monitoring, to disaster relief, to resource planning, among others. The images can be corrupted due to a number of reasons, including instrument errors and natural obstacles such as clouds. We present here a novel approach for reconstruction of missing information in such cases using only the corrupted image as the input. The Deep Image Prior methodology eliminates the need for a pre-trained network or an image database. It is shown that the approach easily beats the performance of traditional single-image methods. Copyright © 2020, The Authors. All rights reserved.

关键词： Disaster prevention

Context-aware Multimodal AI Reveals Hidden Pathways in Five Centuries of Art Evolution

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Kim, Jin Lee, Byunghwee You, Taekho Yun, Jinhyuk Department of Intelligent Semiconductors Soongsil University Seoul06978 Korea Republic of School of Digital Humanities & Computational Social Sciences Korea Advanced Institute of Science and Technology Daejeon34141 Korea Republic of Luddy School of Informatics Computing and Engineering Indiana University BloomingtonIN47408 United States Institute for Social Data Science Pohang University of Science and Technology Pohang37673 Korea Republic of Center for Digital Humanities & Computational Social Sciences Korea Advanced Institute of Science and Technology Daejeon34141 Korea Republic of School of AI Convergence Soongsil University Seoul06978 Korea Republic of

The rise of multimodal generative AI is transforming the intersection of technology and art, offering deeper insights into large-scale artwork. Although its creative capabilities have been widely explored, its potential to represent artwork in latent spaces remains underexamined. We use cutting-edge generative AI, specifically Stable Diffusion, to analyze 500 years of Western paintings by extracting two types of latent information with the model: formal aspects (e.g., colors) and contextual aspects (e.g., subject). Our findings reveal that contextual information differentiates between artistic periods, styles, and individual artists more successfully than formal elements. Additionally, using contextual keywords extracted from paintings, we show how artistic expression evolves alongside societal changes. Our generative experiment, infusing prospective contexts into historical artworks, successfully reproduces the evolutionary trajectory of artworks, highlighting the significance of mutual interaction between society and art. This study demonstrates how multimodal AI expands traditional formal analysis by integrating temporal, cultural, and historical contexts. Copyright © 2025, The Authors. All rights reserved.

关键词： Generative adversarial networks

Deep learning-based large-scale named entity recognition for anatomical region of mammalian brain

学校读者我要写书评

暂无评论

Quantitative Biology 2022年第3期10卷 253-263页

作者： Xiaokang Chai Yachao Di Zhao Feng Yue Guan Guoqing Zhang Anan Li Qingming Luo Britton Chance Center for Biomedical Photonics Wuhan National Laboratory for OptoelectronicsMoE Key Laboratory for Biomedical PhotonicsHuazhong University of Science and TechnologyWuhan 430074China Key Laboratory of Biomedical Engineering of Hainan Province School of Biomedical EngineeringHainan UniversityHaikou 570228China CAS Key Laboratory of Computational Biology Bio-Med Big Data CenterShanghai Institute of Nutrition and HealthUniversity of Chinese Academy of SciencesShanghai 200031China Research Unit of Multimodal Cross Scale Neural Signal Detection and Imaging Chinese Academy of Medical SciencesHUST-Suzhou Institute for BrainsmaticsJITRISuzhou 215123China CAS Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of SciencesShanghai 200031China

Background:Images of anatomical regions and neuron type distribution,as well as their related literature are valuable assets for neuroscience *** are vital evidence and vehicles in discovering new phenomena and knowledge refinement through image and text big *** knowledge acquired from image data generally echoes with the literature accumulated over the *** knowledge within the literature can provide a comprehensive context for a deeper understanding of the image ***,it is quite a challenge to manually identify the related literature and summarize the neuroscience knowledge in the large-scale ***,neuroscientists are in dire need of an automated method to extract neuroscience knowledge from large-scale ***:A proposed deep learning model named BioBERT-CRF extracts brain region entities from the WhiteText *** model takes advantage of BioBERT and CRF to predict entity labels while ***:The proposed deep learning model demonstrated comparable performance against or even outperforms the previous models on the WhiteText *** BioBERT-CRF model has achieved the best average precision,recall,and F1 score of 81.3%,84.0%,and 82.6%,*** used the BioBERT-CRF model to predict brain region entities in a large-scale PubMed abstract dataset and used a rule-based method to normalize all brain region entities to three neuroscience ***:Our work shows that the BioBERT-CRF model can be well-suited for brain region entity *** rankings of different brain region entities by their appearance in the large-scale corpus indicate the anatomical regions that researchers are most concerned about.

关键词： brain region entity extraction literature mining WhiteText deep learning