检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Jacobs, Leah A. McClean, Alec Branson, Zach Kennedy, Edward Fixler, Alex School of Social Work University of Pittsburgh PittsburghPA United States Statistics and Data Science Department Dietrich School of Humanities and Social Sciences Carnegie Mellon University PittsburghPA United States School of Social Work 2217D Cathedral of Learning 4200 Fifth Avenue PittsburghPA15260 United States

Objectives: This study examines the relationship between homelessness and recidivism among people on probation with and without behavioral health problems. The study also illustrates a new way to summarize the effect of an exposure on an outcome, the Incremental Propensity Score (IPS) effect, which avoids pitfalls of other approaches commonly used in criminology. Methods: We assessed the impact of homelessness at probation start on rearrest within one year among a cohort of people on probation (n = 2,453). We estimated IPS effects, considering general and crime-specific recidivism if subjects were more or less likely to be unhoused, and assessed effect variation by behavioral health problem status. We used a doubly robust machine learning estimator to flexibly but efficiently estimate effects. Results: A substantial intervention – reducing homelessness by roughly 65% – corresponded to a 9% reduction in the estimated average rate of recidivism (p © 2023, CC BY.

关键词：

From Pixels to Histopathology: A Graph-Based Framework for Interpretable Whole Slide Image Analysis

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Weers, Alexander Berger, Alexander H. Lux, Laurin Schüffler, Peter Rueckert, Daniel Paetzold, Johannes C. School of Computation Information and Technology Technical University of Munich Germany Department of Computing Imperial College London United Kingdom Munich Center of Machine Learning Germany Munich Data Science Institute Technical University of Munich Munich Germany Institute of Pathology TUM School of Medicine and Health Technical University of Munich Munich Germany Weill Cornell Medicine Cornell University New York CityNY United States

The histopathological classification of whole-slide images (WSIs) is a fundamental task in digital pathology;yet it requires extensive time and expertise from specialists. While deep learning methods show promising results, they typically process WSIs by dividing them into artificial patches, which inherently prevents a network from learning from the entire image context, disregards natural tissue structures and compromises interpretability. Our method overcomes this limitation through a novel graph-based framework that constructs WSI graph representations. The WSI-graph efficiently captures essential histopathological information in a compact form. We build tissue representations (nodes) that follow biological boundaries rather than arbitrary patches all while providing interpretable features for explainability. Through adaptive graph coarsening guided by learned embeddings, we progressively merge regions while maintaining discriminative local features and enabling efficient global information exchange. In our method’s final step, we solve the diagnostic task through a graph attention network. We empirically demonstrate strong performance on multiple challenging tasks such as cancer stage classification and survival prediction, while also identifying predictive factors using Integrated Gradients. Our implementation is publicly available at https://***/HistoGraph31/pix2pathology © 2025, CC BY.

关键词： Classification (of information)

Touchstone benchmark: are we on the right way for evaluating AI algorithms for medical segmentation? 24

学校读者我要写书评

暂无评论

Touchstone benchmark: are we on the right way for evaluating...

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Pedro R. A. S. Bassi Wenxuan Li Yucheng Tang Fabian Isensee Zifu Wang Jieneng Chen Yu-Cheng Chou Saikat Roy Yannick Kirchhoff Maximilian Rokuss Ziyan Huang Jin Ye Junjun He Tassilo Wald Constantin Ulrich Michael Baumgartner Klaus H. Maier-Hein Paul Jaeger Yiwen Ye Yutong Xie Jianpeng Zhang Ziyang Chen Yong Xia Zhaohu Xing Lei Zhu Yousef Sadegheih Afshin Bozorgpour Pratibha Kumari Reza Azad Dorit Merhof Pengcheng Shi Ting Ma Yuxin Du Fan Bai Tiejun Huang Bo Zhao Haonan Wang Xiaomeng Li Hanxue Gu Haoyu Dong Jichen Yang Maciej A. Mazurowski Saumya Gupta Linshan Wu Jiaxin Zhuang Hao Chen Holger Roth Daguang Xu Matthew B. Blaschko Sergio Decherchi Andrea Cavalli Alan L. Yuille Zongwei Zhou Department of Computer Science Johns Hopkins University and Department of Pharmacy and Biotechnology University of Bologna and Center for Biomolecular Nanotechnologies Istituto Italiano di Tecnologia Department of Computer Science Johns Hopkins University NVIDIA Division of Medical Image Computing German Cancer Research Center (DKFZ) and Helmholtz Imaging German Cancer Research Center (DKFZ) ESAT-PSI KU Leuven Division of Medical Image Computing German Cancer Research Center (DKFZ) and Faculty of Mathematics and Computer Science Heidelberg University Division of Medical Image Computing German Cancer Research Center (DKFZ) and Faculty of Mathematics and Computer Science Heidelberg University and HIDSS4Health - Helmholtz Information and Data Science School for Health Shanghai Jiao Tong University Shanghai Artificial Intelligence Laboratory Division of Medical Image Computing German Cancer Research Center (DKFZ) Division of Medical Image Computing German Cancer Research Center (DKFZ) and Pattern Analysis and Learning Group Department of Radiation Oncology Heidelberg University Hospital Helmholtz Imaging German Cancer Research Center (DKFZ) and Interactive Machine Learning Group (IML) DKFZ School of Computer Science and Engineering Northwestern Polytechnical University Australian Institute for Machine Learning The University of Adelaide College of Computer Science and Technology Zhejiang University Hong Kong University of Science and Technology (Guangzhou) Hong Kong University of Science and Technology (Guangzhou) and Hong Kong University of Science and Technology Faculty of Informatics and Data Science University of Regensburg Faculty of Electrical Engineering and Information Technology RWTH Aachen University Faculty of Informatics and Data Science University of Regensburg and Fraunhofer Institute for Digital Medicine MEVIS Electronic & Information Engineering School Harbin Institute of Technology (Shenzhen) Shanghai Jiao Tong University and Beijing Academy of Artificial Intelligence (BAAI) S

ISBN: (纸本)9798331314385

How can we test AI performance? This question seems trivial, but it isn't. Standard benchmarks often have problems such as in-distribution and small-size test sets, oversimplified metrics, unfair comparisons, and short-term outcome pressure. As a consequence, good performance on standard benchmarks does not guarantee success in real-world scenarios. To address these problems, we present Touchstone, a large-scale collaborative segmentation benchmark of 9 types of abdominal organs. This benchmark is based on 5,195 training CT scans from 76 hospitals around the world and 5,903 testing CT scans from 11 additional hospitals. This diverse test set enhances the statistical significance of benchmark results and rigorously evaluates AI algorithms across out-of-distribution scenarios. We invited 14 inventors of 19 AI algorithms to train their algorithms, while our team, as a third party, independently evaluated these algorithms. In addition, we also evaluated pre-existing AI frameworks—which, differing from algorithms, are more flexible and can support different algorithms—including MONAI from NVIDIA, nnU-Net from DKFZ, and numerous other open-source frameworks. We are committed to expanding this benchmark to encourage more innovation of AI algorithms for the medical domain.

关键词：

CLOUD CLASSIFICATION WITH UNSUPERVISED DEEP learning

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Kurihana, Takuya Foster, Ian Willett, Rebecca Jenkins, Sydney Koenig, Kathryn Werman, Ruby Lourenco, Ricardo Barros Neo, Casper Moyer, Elisabeth Department of Computer Science University of Chicago United States Data Science and Learning Division Argonne National Lab United States Department of the Geophysical Sciences University of Chicago United States Department of Statistics University of Chicago United States Department of Physics University of Chicago United States Harris School of Public Policy University of Chicago United States College of Letters & Science University of California Berkeley United States

We present a framework for cloud characterization that leverages modern unsupervised deep learning technologies. While previous neural network-based cloud classification models have used supervised learning methods, unsupervised learning allows us to avoid restricting the model to artificial categories based on historical cloud classification schemes and enables the discovery of novel, more detailed classifications. Our framework learns cloud features directly from radiance data produced by NASA's Moderate Resolution Imaging Spectroradiometer (MODIS) satellite instrument, deriving cloud characteristics from millions of images without relying on pre-defined cloud types during the training process. We present preliminary results showing that our method extracts physically relevant information from radiance data and produces meaningful cloud classes. © 2022, CC BY.

关键词： Deep learning

OADAT: Experimental and Synthetic Clinical Optoacoustic data for Standardized Image Processing

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Ozdemir, Firat Lafci, Berkan Deán-Ben, Xosé Luís Razansky, Daniel Perez-Cruz, Fernando Swiss Data Science Center ETH Zurich and EPFL Zurich Switzerland Institute of Pharmacology and Toxicology Institute for Biomedical Engineering Faculty of Medicine University of Zurich Switzerland Institute for Biomedical Engineering Department of Information Technology and Electrical Engineering ETH Zurich Switzerland Institute for Machine Learning Department of Computer Science ETH Zurich Switzerland

Optoacoustic (OA) imaging is based on excitation of biological tissues with nanosecond-duration laser pulses followed by subsequent detection of ultrasound waves generated via light-absorption-mediated thermoelastic expansion. OA imaging features a powerful combination between rich optical contrast and high resolution in deep tissues. This enabled the exploration of a number of attractive new applications both in clinical and laboratory settings. However, no standardized datasets generated with different types of experimental set-up and associated processing methods are available to facilitate advances in broader applications of OA in clinical settings. This complicates an objective comparison between new and established data processing methods, often leading to qualitative results and arbitrary interpretations of the data. In this paper, we provide both experimental and synthetic OA raw signals and reconstructed image domain datasets rendered with different experimental parameters and tomographic acquisition geometries. We further provide trained neural networks to tackle three important challenges related to OA image processing, namely accurate reconstruction under limited view tomographic conditions, removal of spatial undersampling artifacts and anatomical segmentation for improved image reconstruction. Specifically, we define 44 experiments corresponding to the aforementioned challenges as benchmarks to be used as a reference for the development of more advanced processing methods. © 2022, CC BY-NC-SA.

关键词： Photoacoustic effect

The Alchemical Integral Transform revisited

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Krug, Simon León von Lilienfeld, O. Anatole Machine Learning Group Technische Universität Berlin Berlin10587 Germany Berlin Institute for the Foundations of Learning and Data Berlin10587 Germany Chemical Physics Theory Group Department of Chemistry University of Toronto St. George Campus TorontoON Canada Department of Materials Science and Engineering University of Toronto St. George Campus TorontoON Canada Vector Institute for Artificial Intelligence TorontoON Canada Department of Physics University of Toronto St. George Campus TorontoON Canada Acceleration Consortium University of Toronto TorontoON Canada

We recently introduced the Alchemical Integral Transform (AIT) enabling the prediction of energy differences, and guessed an Ansatz to parametrize space r in some alchemical change λ. Here, we present a rigorous derivation of AIT’s kernel K and discuss the parametrization r(λ) in n dimensions, i.e. necessary conditions, mathematical freedoms and additional constraints when obtaining it. Analytical expressions for changes in energy spectra and densities are given for a number of systems. Examples include homogeneous potentials like the quantum harmonic oscillator, Hydrogen-like atom, and Dirac well, both for one- and multiparticle cases, and a multiparticle system beyond coordinate scaling for harmonic potentials. © 2023, CC BY.

关键词： Choquet integral

Generalized Independent Noise Condition for Estimating Causal Structure with Latent Variables

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Xie, Feng Huang, Biwei Chen, Zhengming Cai, Ruichu Glymour, Clark Geng, Zhi Zhang, Kun Department of Applied Statistics Beijing Technology and Business University Beijing102488 China University of California San Diego La Jolla San DiegoCA92093 United States School of Computer Science Guangdong University of Technology Guangzhou510006 China Machine Learning Department Mohamed bin Zayed University of Artificial Intelligence Abu Dhabi United Arab Emirates Department of Philosophy Carnegie Mellon University PittsburghPA15213 United States

We investigate the challenging task of learning causal structure in the presence of latent variables, including locating latent variables, determining their quantity, and identifying causal relationships among both latent and observed variables. To address this, we propose a Generalized Independent Noise (GIN) condition for linear non-Gaussian acyclic causal models that incorporate latent variables, which establishes the independence between a linear combination of certain measured variables and some other measured variables. Specifically, for two observed random vectors Y and Z, GIN holds if and only if ωY and Z are statistically independent, where ω is a non-zero parameter vector determined by the cross-covariance between Y and Z. We then give necessary and sufficient graphical criteria of the GIN condition in linear non-Gaussian acyclic causal models. From a graphical perspective, roughly speaking, GIN implies the existence of a set S such that S is causally earlier (w.r.t. the causal ordering) than Y, and that every active (collider-free) path between Y and Z must contain a node from S. Interestingly, we find that the independent noise condition (i.e., if there is no confounder, causes are independent of the residual derived from regressing the effect on the causes) can be seen as a special case of GIN. With such a connection between GIN and latent causal structures, we further leverage the proposed GIN condition, together with a well-designed search procedure, to efficiently estimate Linear, Non-Gaussian Latent Hierarchical Models (LiNGLaHs), where latent confounders may also be causally related and may even follow a hierarchical structure. We show that the underlying causal structure of a LiNGLaH is identifiable in light of GIN conditions under mild assumptions. Experimental results on both synthetic and three real-world data sets show the effectiveness of the proposed approach. Copyright © 2023, The Authors. All rights reserved.

关键词： Gaussian distribution

Distribution-free binary classification: Prediction sets, confidence intervals and calibration

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Gupta, Chirag Podkopaev, Aleksandr Ramdas, Aaditya Machine Learning Department Carnegie Mellon University United States Department of Statistics and Data Science Carnegie Mellon University United States

We study three notions of uncertainty quantification-calibration, confidence intervals and prediction sets-for binary classification in the distribution-free setting, that is without making any distributional assumptions on the data. With a focus towards calibration, we establish a 'tripod' of theorems that connect these three notions for score-based classifiers. A direct implication is that distribution-free calibration is only possible, even asymptotically, using a scoring function whose level sets partition the feature space into at most countably many sets. Parametric calibration schemes such as variants of Platt scaling do not satisfy this requirement, while nonparametric schemes based on binning do. To close the loop, we derive distribution-free confidence intervals for binned probabilities for both fixed-width and uniform-mass binning. As a consequence of our 'tripod' theorems, these confidence intervals for binned probabilities lead to distribution-free calibration. We also derive extensions to settings with streaming data and covariate shift. Copyright © 2020, The Authors. All rights reserved.

关键词： Calibration

On conditional versus marginal bias in multi-armed bandits

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Shin, Jaehyeok Rinaldo, Alessandro Ramdas, Aaditya Department of Statistics and Data Science Carnegie Mellon University United States Machine Learning Department Carnegie Mellon University United States

The bias of the sample means of the arms in multiarmed bandits is an important issue in adaptive data analysis that has recently received considerable attention in the literature. Existing results relate in precise ways the sign and magnitude of the bias to various sources of data adaptivity, but do not apply to the conditional inference setting in which the sample means are computed only if some specific conditions are satisfied. In this paper, we characterize the sign of the conditional bias of monotone functions of the rewards, including the sample mean. Our results hold for arbitrary conditioning events and leverage natural monotonicity properties of the data collection policy. We further demonstrate, through several examples from sequential testing and best arm identification, that the sign of the conditional and marginal bias of the sample mean of an arm can be different, depending on the conditioning event. Our analysis offers new and interesting perspectives on the subtleties of assessing the bias in data adaptive settings. Copyright © 2020, The Authors. All rights reserved.

关键词： machine learning

Schedule-Robust Online Continual learning

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wang, Ruohan Ciccone, Marco Luise, Giulia Pontil, Massimiliano Yapp, Andrew Ciliberto, Carlo Singapore Politecnico di Torino Torino Italy Centre for Artificial Intelligence Department of Computer Science University College London United Kingdom Computational Statistics and Machine Learning Group Istituto Italiano di Tecnologia Genova Italy National University of Singapore Singapore

A continual learning (CL) algorithm learns from a non-stationary data stream. The non-stationarity is modeled by some schedule that determines how data is presented over time. Most current methods make strong assumptions on the schedule and have unpredictable performance when such requirements are not met. A key challenge in CL is thus to design methods robust against arbitrary schedules over the same underlying data, since in real-world scenarios schedules are often unknown and dynamic. In this work, we introduce the notion of schedule-robustness for CL and a novel approach satisfying this desirable property in the challenging online class-incremental setting. We also present a new perspective on CL, as the process of learning a schedule-robust predictor, followed by adapting the predictor using only replay data. Empirically, we demonstrate that our approach outperforms existing methods on CL benchmarks for image classification by a large margin. © 2022, CC BY.

关键词： E-learning