检索结果-内蒙古大学图书馆

35th Annual Conference on Neural Information Processing Systems (NeurIPS)

作者： Zhu, Feng Sedler, Andrew R. Grier, Harrison A. Ahad, Nauman Davenport, Mark A. Kaufman, Matthew T. Giovannucci, Andrea Pandarinath, Chethan Emory Univ Neurosci Grad Program Atlanta GA 30322 USA Georgia Tech Ctr Machine Learning Atlanta GA 30332 USA Univ Chicago Computat Neurosci Grad Program Chicago IL 60637 USA Georgia Tech Sch Elect & Comp Engn Atlanta GA USA Univ Chicago Dept Organismal Biol & Anat Chicago IL 60637 USA Univ Chicago Neurosci Inst Chicago IL 60637 USA UNC Chapel Hill Joint Dept Biomed Engn Chapel Hill NC USA NC State Univ Chapel Hill NC USA UNC Chapel Hill Neurosci Ctr Chapel Hill NC USA UNC Closed Loop Engn Adv Rehabil CLEAR NC State Chapel Hill NC USA Emory Univ Coulter Dept Biomed Engn Atlanta GA 30322 USA Georgia Tech Atlanta GA 30332 USA Emory Univ Dept Neurosurg Atlanta GA 30322 USA

ISBN: (纸本)9781713845393

Modern neural interfaces allow access to the activity of up to a million neurons within brain circuits. However, bandwidth limits often create a trade-off between greater spatial sampling (more channels or pixels) and the temporal frequency of sampling. Here we demonstrate that it is possible to obtain spatio-temporal super-resolution in neuronal time series by exploiting relationships among neurons, embedded in latent low-dimensional population dynamics. Our novel neural network training strategy, selective backpropagation through time (SBTT), enables learning of deep generative models of latent dynamics from data in which the set of observed variables changes at each time step. The resulting models are able to infer activity for missing samples by combining observations with learned latent dynamics. We test SBTT applied to sequential autoencoders and demonstrate more efficient and higher-fidelity characterization of neural population dynamics in electrophysiological and calcium imaging data. In electrophysiology, SBTT enables accurate inference of neuronal population dynamics with lower interface bandwidths, providing an avenue to significant power savings for implanted neuroelectronic interfaces. In applications to two-photon calcium imaging, SBTT accurately uncovers high-frequency temporal structure underlying neural population activity, substantially outperforming the current state-of-the-art. Finally, we demonstrate that performance could be further improved by using limited, highbandwidth sampling to pretrain dynamics models, and then using SBTT to adapt these models for sparsely-sampled data.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

Deep inference of latent dynamics with spatio-temporal super-resolution using selective backpropagation through time

arXiv

引用

arXiv 2021年

作者： Zhu, Feng Sedler, Andrew R. Grier, Harrison A. Ahad, Nauman Davenport, Mark A. Kaufman, Matthew T. Giovannucci, Andrea Pandarinath, Chethan Neuroscience Graduate Program Emory University Center for Machine Learning Georgia Tech Computational Neuroscience Graduate Program The University of Chicago School of Electrical and Computer Engineering Georgia Tech Dept. of Organismal Biology and Anatomy The University of Chicago Neuroscience Institute The University of Chicago Joint Dept. of Biomedical Engineering UNC Chapel Hill NC State University UNC Chapel Hill Neuroscience Center Coulter Dept. of Biomedical Engineering Emory University Georgia Tech Dept. of Neurosurgery Emory University

Modern neural interfaces allow access to the activity of up to a million neurons within brain circuits. However, bandwidth limits often create a trade-off between greater spatial sampling (more channels or pixels) and the temporal frequency of sampling. Here we demonstrate that it is possible to obtain spatio-temporal super-resolution in neuronal time series by exploiting relationships among neurons, embedded in latent low-dimensional population dynamics. Our novel neural network training strategy, selective backpropagation through time (SBTT), enables learning of deep generative models of latent dynamics from data in which the set of observed variables changes at each time step. The resulting models are able to infer activity for missing samples by combining observations with learned latent dynamics. We test SBTT applied to sequential autoencoders and demonstrate more efficient and higher-fidelity characterization of neural population dynamics in electrophysiological and calcium imaging data. In electrophysiology, SBTT enables accurate inference of neuronal population dynamics with lower interface bandwidths, providing an avenue to significant power savings for implanted neuroelectronic interfaces. In applications to two-photon calcium imaging, SBTT accurately uncovers high-frequency temporal structure underlying neural population activity, substantially outperforming the current state-of-the-art. Finally, we demonstrate that performance could be further improved by using limited, high-bandwidth sampling to pretrain dynamics models, and then using SBTT to adapt these models for sparsely-sampled data. © 2021, CC BY-NC-SA.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

Beyond Ultra-diffuse Galaxies. I. Mass-Size Outliers among the Satellites of Milky Way Analogs

引用

ASTROPHYSICAL JOURNAL 2023年第1期955卷 1-1页

作者： Li, Jiaxuan Greene, Jenny E. Greco, Johnny P. Huang, Song Melchior, Peter Beaton, Rachael Casey, Kirsten Danieli, Shany Goulding, Andy Joseph, Remy Kado-Fong, Erin Kim, Ji Hoon Macarthur, Lauren A. Princeton Univ Dept Astrophys Sci 4 Ivy Lane Princeton NJ 08544 USA Ohio State Univ Ctr Cosmol & Astro Particle Phys CCAPP Columbus OH 43210 USA Tsinghua Univ Dept Astron Beijing 100084 Peoples R China Tsinghua Univ Tsinghua Ctr Astrophys Beijing 100084 Peoples R China Princeton Univ Ctr Stat & Machine Learning Princeton NJ 08544 USA Stockholm Univ Oskar Klein Ctr Cosmoparticle Phys Dept Phys SE-10691 Stockholm Sweden Seoul Natl Univ Dept Phys & Astron Astron Program 1 Gwanak Ro Seoul 08826 South Korea Seoul Natl Univ SNU Astron Res Ctr 1 Gwanak Ro Seoul 08826 South Korea

Large diffuse galaxies are hard to find, but understanding the environments where they live, their numbers, and ultimately their origins, is of intense interest and importance for galaxy formation and evolution. Using Subaru's Hyper Suprime-Cam Strategic Survey program, we perform a systematic search for low surface brightness galaxies and present novel and effective methods for detecting and modeling them. As a case study, we surveyed 922 Milky Way analogs in the nearby Universe (0.01 < z < 0.04) and built a large sample of satellite galaxies that are outliers in the mass-size relation. These "ultra-puffy" galaxies ( UPGs), defined to be 1.5s above the average mass-size relation, represent the tail of the satellite size distribution. We find that each MW analog hosts NUPG = 0.31 +/- 0.05 UPGs on average, which is consistent with but slightly lower than the observed abundance at this halo mass in the Local Volume. We also construct a sample of ultra-diffuse galaxies (UDGs) in MW analogs and find an abundance of NUDG = 0.44 +/- 0.05 per host. With literature results, we confirm that the UDG abundance scales with the host halo mass following a sublinear power law. We argue that our definition of UPGs, which is based on the mass-size relation, is more physically motivated than the common definition of UDGs, which depends on the surface brightness and size cuts and thus yields different surface mass density cuts for quenched and star-forming galaxies. Unified Astronomy Thesaurus concepts: Low surface brightness galaxies (940);Dwarf galaxies (416);Galaxy properties (615);Galaxy abundances (574)

关键词：

来源：评论

学校读者我要写书评

暂无评论

Making transport more robust and interpretable by moving data through a small number of anchor points

arXiv

引用

arXiv 2020年

作者： Lin, Chi-Heng Azabou, Mehdi Dyer, Eva L. Department of Electrical and Computer Engineering Georgia Tech AtlantaGA United States Machine Learning Program Georgia Tech AtlantaGA United States Coulter Department of Biomedical Engineering Georgia Tech & Emory University AtlantaGA United States

Optimal transport (OT) is a widely used technique for distribution alignment, with applications throughout the machine learning, graphics, and vision communities. Without any additional structural assumptions on transport, however, OT can be fragile to outliers or noise, especially in high dimensions. Here, we introduce Latent Optimal Transport (LOT), a new approach for OT that simultaneously learns low-dimensional structure in data while leveraging this structure to solve the alignment task. The idea behind our approach is to learn two sets of "anchors" that constrain the flow of transport between a source and target distribution. In both theoretical and empirical studies, we show that LOT regularizes the rank of transport and makes it more robust to outliers and the sampling density. We show that by allowing the source and target to have different anchors, and using LOT to align the latent spaces between anchors, the resulting transport plan has better structural interpretability and highlights connections between both the individual data points and the local geometry of the datasets. Copyright © 2020, The Authors. All rights reserved.

关键词： Anchors

来源：评论

学校读者我要写书评

暂无评论

Genome-Wide CRISPR-Cas9 Screening Identifies a Synergy between Hypomethylating Agents and Sumoylation Blockade in Myelodysplastic Syndromes and Acute Myeloid Leukemia

引用

BLOOD 2022年第Sup1期140卷 220-221页

作者： Truong, Peter Shen, Sylvie Joshi, Swapna Afrasiabi, Ali Zhong, Ling Raftery, Mark J. Larsson, Jonas Lock, Richard B. Walkley, Carl R. Rokny, Hamid Alinejad Thoms, Julie A. I. Jolly, Christopher J. Pimanda, John E. Univ New South Wales Sch Clin Med Sydney NSW Australia Univ New South Wales Grad Sch Biomed Engn BioMed Machine Learning Lab Sydney NSW Australia Univ New South Wales Bioanalyt Mass Spectrometry Facil Sydney NSW Australia Lund Univ Div Mol Med & Gene Therapy Lund Stem Cell Ctr Lund Sweden Univ New South Wales Sch Womens & Childrens Hlth Sydney NSW Australia Univ New South Wales Childrens Canc Inst Sydney NSW Australia Univ New South Wales Ctr Childhood Canc Res Sydney NSW Australia Univ Melbourne St Vincents Inst Melbourne Vic Australia Univ Melbourne Med Melbourne Vic Australia Univ New South Wales UNSW Data Sci Hub Sydney NSW Australia Macquarie Univ Hlth Data Analyt Program AI Enabled Proc Res Ctr Sydney NSW Australia Univ New South Wales Sch Med Sci Randwick NSW Australia Prince Wales Hosp Dept Haematol Sydney NSW Australia

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

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.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Reliable Radiologic Skeletal Muscle Area Assessment – A Biomarker for Cancer Cachexia Diagnosis

arXiv

引用

arXiv 2025年

作者： Ahmed, Sabeen Parker, Nathan Park, Margaret Jeong, Daniel Peres, Lauren Davis, Evan W. Permuth, Jennifer B. Siegel, Erin Schabath, Matthew B. Yilmaz, Yasin Rasool, Ghulam Department of Machine Learning H. Lee Moffitt Cancer Center and Research Institute TampaFL United States Department of Health Outcomes and Behavior H. Lee Moffitt Cancer Center and Research Institute TampaFL United States Department of GI Oncology H. Lee Moffitt Cancer Center and Research Institute TampaFL United States Diagnostic Imaging and Interventional Radiology H. Lee Moffitt Cancer Center and Research Institute TampaFL United States Department of Cancer Epidemiology H. Lee Moffitt Cancer Center and Research Institute TampaFL United States Department of Biostatistics and Bioinformatics H. Lee Moffitt Cancer Center and Research Institute TampaFL United States Department of Electrical Engineering University of South Florida TampaFL United States Epidemiology and Genomics Research Program National Cancer Institute NIH United States

Cancer cachexia is a common metabolic disorder characterized by severe muscle atrophy which is associated with poor prognosis and quality of life. Monitoring skeletal muscle area (SMA) longitudinally through computed tomography (CT) scans, an imaging modality routinely acquired in cancer care, is an effective way to identify and track this condition. However, existing tools often lack full automation and exhibit inconsistent accuracy, limiting their potential for integration into clinical workflows. To address these challenges, we developed SMAART-AI (Skeletal Muscle Assessment-Automated and Reliable Tool-based on AI), an end-to-end automated pipeline powered by deep learning models (nnU-Net 2D) trained on mid-third lumbar level CT images with 5-fold cross-validation, ensuring generalizability and robustness. SMAART-AI incorporates an uncertainty-based mechanism to flag high-error SMA predictions for expert review, enhancing reliability. We combined the SMA, skeletal muscle index, BMI, and clinical data to train a multi-layer perceptron (MLP) model designed to predict cachexia at the time of cancer diagnosis. Tested on the gastroesophageal cancer dataset, SMAART-AI achieved a Dice score of 97.80% ± 0.93%, with SMA estimated across all four datasets in this study at a median absolute error of 2.48% compared to manual annotations with SliceOmatic. Uncertainty metrics—variance, entropy, and coefficient of variation—strongly correlated with SMA prediction errors (0.83, 0.76, and 0.73 respectively). The MLP model predicts cachexia with 79% precision, providing clinicians with a reliable tool for early diagnosis and intervention. By combining automation, accuracy, and uncertainty awareness, SMAART-AI bridges the gap between research and clinical application, offering a transformative approach to managing cancer cachexia. © 2025, CC BY-NC-ND.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Cross-population coupling of neural activity based on Gaussian process current source densities

arXiv

引用

arXiv 2021年

作者： Klein, Natalie Siegle, Joshua H. Teichert, Tobias Kass, Robert E. Department of Statistics and Data Science Carnegie Mellon University PittsburghPA United States Machine Learning Department Carnegie Mellon University PittsburghPA United States MindScope Program Allen Institute SeattleWA United States Department of Psychiatry University of Pittsburgh PittsburghPA United States Department of Bioengineering University of Pittsburgh PittsburghPA United States Neuroscience Institute Carnegie Mellon University PittsburghPA United States

Because local field potentials (LFPs) arise from multiple sources in different spatial locations, they do not easily reveal coordinated activity across neural populations on a trial-to-trial basis. As we show here, however, once disparate source signals are decoupled, their trial-to-trial fluctuations become more accessible, and cross-population correlations become more apparent. To decouple sources we introduce a general framework for estimation of current source densities (CSDs). In this framework, the set of LFPs result from noise being added to the transform of the CSD by a biophysical forward model, while the CSD is considered to be the sum of a zero-mean, stationary, spatiotemporal Gaussian process, having fast and slow components, and a mean function, which is the sum of multiple time-varying functions distributed across space, each varying across trials. We derived biophysical forward models relevant to the data we analyzed. In simulation studies this approach improved identification of source signals compared to existing CSD estimation methods. Using data recorded from primate auditory cortex, we analyzed trial-to-trial fluctuations in both steady-state and task-evoked signals. We found cortical layer-specific phase coupling between two probes and showed that the same analysis applied directly to LFPs did not recover these patterns. We also found task-evoked CSDs to be correlated across probes, at specific cortical depths. Using data from Neuropixels probes in mouse visual areas, we again found evidence for depth-specific phase coupling of primary visual cortex and lateromedial area based on the CSDs. © 2021, CC BY.

关键词： Probes

来源：评论

学校读者我要写书评

暂无评论

Deep learning for Classification and Localization of COVID-19 Markers in Point-of-Care Lung Ultrasound

引用

IEEE TRANSACTIONS ON MEDICAL IMAGING 2020年第8期39卷 2676-2687页

作者： Roy, Subhankar Menapace, Willi Oei, Sebastiaan Luijten, Ben Fini, Enrico Saltori, Cristiano Huijben, Iris Chennakeshava, Nishith Mento, Federico Sentelli, Alessandro Peschiera, Emanuele Trevisan, Riccardo Maschietto, Giovanni Torri, Elena Inchingolo, Riccardo Smargiassi, Andrea Soldati, Gino Rota, Paolo Passerini, Andrea van Sloun, Ruud J. G. Ricci, Elisa Demi, Libertario Univ Trento Dept Informat Engn & Comp Sci Deep & Struct Machine Learning Res Program I-38123 Trento Italy Fdn Bruno Kessler I-38123 Trento Italy Eindhoven Univ Technol Dept Elect Engn NL-5612 Eindhoven Netherlands Univ Trento Dept Informat Engn & Comp Sci Ultrasound Lab Trento ULTRa I-38123 Trento Italy BresciaMEd I-25128 Brescia Italy Fdn Policlin Univ Agostino Gemelli IRCCS Dept Cardiovasc & Thorac Sci I-00168 Rome Italy Valle Serchio Gen Hosp Diagnost & Intervent Ultrasound Unit I-55100 Lucca Italy Fdn Policlin Univ Agostino Gemelli IRCCS Dept Med & Surg Sci Rome Italy

Deep learning (DL) has proved successful in medical imaging and, in the wake of the recent COVID-19 pandemic, some works have started to investigate DL-based solutions for the assisted diagnosis of lung diseases. While existing works focus on CT scans, this paper studies the application of DL techniques for the analysis of lung ultrasonography (LUS) images. Specifically, we present a novel fully-annotated dataset of LUS images collected from several Italian hospitals, with labels indicating the degree of disease severity at a frame-level, video-level, and pixel-level (segmentation masks). Leveraging these data, we introduce several deep models that address relevant tasks for the automatic analysis of LUS images. In particular, we present a novel deep network, derived from Spatial Transformer Networks, which simultaneously predicts the disease severity score associated to a input frame and provides localization of pathological artefacts in a weakly-supervised way. Furthermore, we introduce a new method based on uninorms for effective frame score aggregation at a video-level. Finally, we benchmark state of the art deep models for estimating pixel-level segmentations of COVID-19 imaging biomarkers. Experiments on the proposed dataset demonstrate satisfactory results on all the considered tasks, paving the way to future research on DL for the assisted diagnosis of COVID-19 from LUS data.

关键词： Image segmentation Lung Ultrasonic imaging Task analysis Pathology Imaging Diseases COVID-19 COVID-19 lung ultrasound deep learning

来源：评论

学校读者我要写书评

暂无评论

Global Land-Cover Mapping With Weak Supervision: Outcome of the 2020 IEEE GRSS Data Fusion Contest

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2021年 14卷 3185-3199页

作者： Robinson, Caleb Malkin, Kolya Jojic, Nebojsa Chen, Huijun Qin, Rongjun Xiao, Changlin Schmitt, Michael Ghamisi, Pedram Haensch, Ronny Yokoya, Naoto Georgia Inst Technol Sch Computat Sci & Engn Atlanta GA 30332 USA Microsoft Res AI Good Res Lab Redmond WA 98052 USA Yale Univ Dept Math New Haven CT 06520 USA Microsoft Res Redmond WA 98052 USA Ohio State Univ Dept Civil Environm & Geodet Engn Columbus OH 43210 USA Ohio State Univ Environm Sci Grad Program Columbus OH 43210 USA Ohio State Univ Dept Civil Environm & Geodet Engn Dept Elect & Comp Engn Columbus OH 43210 USA Ohio State Univ Translat Data Analyt Inst Columbus OH 43210 USA Munich Univ Appl Sci Dept Geoinformat D-80335 Munich Germany Helmholtz Zentrum Dresden Rossendorf Machine Learning Grp Helmholtz Inst Freiberg Resource Technol D-09599 Freiberg Germany German Aerosp Ctr D-82234 Wessling Germany Univ Tokyo Dept Complex Sci & Engn Chiba 2778561 Japan RIKEN Ctr Adv Intelligence Project Tokyo 1030027 Japan

This article presents the scientific outcomes of the 2020 Data Fusion Contest (DFC2020) organized by the Image Analysis and Data Fusion Technical Committee of the IEEE Geoscience and Remote Sensing Society. The 2020 Contest addressed the problem of automatic global land-cover mapping with weak supervision, i.e., estimating high-resolution semantic maps while only low-resolution reference data are available during training. Two separate competitions were organized to assess two different scenarios: 1) high-resolution labels are not available at all;and 2) a small amount of high-resolution labels are available additionally to low-resolution reference data. In this article, we describe the DFC2020 dataset that remains available for further evaluation of corresponding approaches and report the results of the best-performing methods during the contest.

关键词： Earth Data integration Remote sensing Satellites Training Tensors Synthetic aperture radar Convolutional neural networks (CNNs) deep learning image analysis and data fusion land-cover mapping multimodal random forests (RFs) weak supervision

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：