检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Akbar, Muhammad Usman Wang, Wuhao Eklund, Anders Division of Medical Informatics Department of Biomedical Engineering Division of Statistics & Machine Learning Department of Computer and Information Science Linköping University Sweden

Diffusion models were initially developed for text-to-image generation and are now being utilized to generate high quality synthetic images. Preceded by GANs, diffusion models have shown impressive results using various evaluation metrics. However, commonly used metrics such as FID and IS are not suitable for determining whether diffusion models are simply reproducing the training images. Here we train StyleGAN and a diffusion model, using BRATS20, BRATS21 and a chest x-ray pneumonia dataset, to synthesize brain MRI and chest x-ray images, and measure the correlation between the synthetic images and all training images. Our results show that diffusion models are more likely to memorize the training images, compared to StyleGAN, especially for small datasets and when using 2D slices from 3D volumes. Researchers should be careful when using diffusion models (and to some extent GANs) for medical imaging, if the final goal is to share the synthetic images. © 2023, CC BY.

关键词： Medical imaging

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 41

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

引用

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

Assumption-Lean Post-Integrated Inference with Negative Control Outcomes

arXiv

引用

arXiv 2024年

作者： Du, Jin-Hong Roeder, Kathryn Wasserman, Larry Department of Statistics and Data Science Carnegie Mellon University PittsburghPA15213 United States Machine Learning Department Carnegie Mellon University PittsburghPA15213 United States Computational Biology Department Carnegie Mellon University PittsburghPA15213 United States

data integration methods aim to extract low-dimensional embeddings from high-dimensional outcomes to remove unwanted variations, such as batch effects and unmeasured covariates, across heterogeneous datasets. However, multiple hypothesis testing after integration can be biased due to data-dependent processes. We introduce a robust post-integrated inference (PII) method that adjusts for latent heterogeneity using negative control outcomes. Leveraging causal interpretations, we derive nonparametric identifiability of the direct effects, which motivates our semiparametric inference method. Our method extends to projected direct effect estimands, accounting for hidden mediators, confounders, and moderators. These estimands remain statistically meaningful under model misspecifications and with error-prone embeddings. We provide bias quantifications and finite-sample linear expansions with uniform concentration bounds. The proposed doubly robust estimators are consistent and efficient under minimal assumptions and potential misspecification, facilitating data-adaptive estimation with machine learning algorithms. Our proposal is evaluated with random forests through simulations and analysis of single-cell CRISPR perturbed datasets with potential unmeasured confounders. Copyright © 2024, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Intelligent Posture Detection System for Improved Ergonomics

Intelligent Posture Detection System for Improved Ergonomics

引用

2025 International Conference on Intelligent Control, Computing and Communications, IC3 2025

作者： Patil, Jay Joshi, Suvarna Mulla, Rahesha Yadav, Kushal Mit School of Computing Mit Adt University Department of Computer Science and Eng. Pune India University Department of Artificial Intelligence and Machine Learning Pune India Indian Institute of Technology Madras Department of Data Science India

ISBN: (纸本)9798331527495

This paper introduces a cost-effective smart posture detection system aimed at promoting ergonomic sitting habits and preventing musculoskeletal disorders. The system integrates ultrasonic sensors for backrest proximity measurement and load cells for seat weight distribution analysis. By analyzing these inputs, it identifies posture irregularities and provides real-time feedback for corrective action. Testing results demonstrate the system's reliability, achieving a detection accuracy of 99% across users with varying body types and postures. The proposed hybrid approach ensures simplicity, affordability, and scalability, making it a viable solution for homes, workplaces, and schools. This research contributes to the growing field of smart health monitoring systems, offering a practical alternative to traditional posture correction methods. © 2025 IEEE.

关键词： Ultrasonic testing

来源：评论

学校读者我要写书评

暂无评论

Optical Character Recognition (OCR) in Handwritten Characters Using Convolutional Neural Networks to Assist in Exam Reader System 2

Optical Character Recognition (OCR) in Handwritten Character...

引用

2nd International Conference on Advancement in Computation and Computer Technologies, InCACCT 2024

作者： Lekshmy, P.L. Velmurugan, S. Kumari, Indra Kayalvili, S. Teja Sree, B. Karthik Kumar, P. LBS Institute of Technology for Women Department of Computer Science and Engineering Kerala India T.J.S. Engineering College Department of Electronics and Communication Engineering Tamil Nadu Chennai India Department of Machine Learning Data Research Applied AI Daejeon Korea Republic of Department of Artificial Intelligence Tamilnadu Erode India S.R.K.R. Engineering College Department of Information Technology Andhra Pradesh Chinaamiram Bhimavaram India Coimbatore India

ISBN: (纸本)9798350371314

This work aimed to develop a character recognition method to facilitate the correction of answer cards in the Multiprova software through the development of a response card analysis flow that would culminate in the recognition of letters written by students and automatic correction of the tests. To isolate and identify the answers written on the answer cards, image segmentation techniques were used based on fixed marks printed on the cards. To recognize the letters and numbers written on the cards, trained three convolutional neural networks (for digits, letters and true or false). The results achieved (98.84% accuracy for digit CNN, 98.38% accuracy for letter CNN and 99.89% accuracy for true or false CNN) point out a great average success rate. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Causal Inference for Genomic data with Multiple Heterogeneous Outcomes

arXiv

引用

arXiv 2024年

作者： Du, Jin-Hong Zeng, Zhenghao Kennedy, Edward H. Wasserman, Larry Roeder, Kathryn Department of Statistics and Data Science Carnegie Mellon University PittsburghPA15213 United States Machine Learning Department Carnegie Mellon University PittsburghPA15213 United States Computational Biology Department Carnegie Mellon University PittsburghPA15213 United States

With the evolution of single-cell RNA sequencing techniques into a standard approach in genomics, it has become possible to conduct cohort-level causal inferences based on single-cell-level measurements. However, the individual gene expression levels of interest are not directly observable;instead, only repeated proxy measurements from each individual’s cells are available, providing a derived outcome to estimate the underlying outcome for each of many genes. In this paper, we propose a generic semiparametric inference framework for doubly robust estimation with multiple derived outcomes, which also encompasses the usual setting of multiple outcomes when the response of each unit is available. To reliably quantify the causal effects of heterogeneous outcomes, we specialize the analysis to standardized average treatment effects and quantile treatment effects. Through this, we demonstrate the use of the semiparametric inferential results for doubly robust estimators derived from both Von Mises expansions and estimating equations. A multiple testing procedure based on Gaussian multiplier bootstrap is tailored for doubly robust estimators to control the false discovery exceedance rate. Applications in single-cell CRISPR perturbation analysis and individual-level differential expression analysis demonstrate the utility of the proposed methods and offer insights into the usage of different estimands for causal inference in genomics. Copyright © 2024, The Authors. All rights reserved.

关键词： Genome

来源：评论

学校读者我要写书评

暂无评论

Probabilistic Task Modelling for Meta-learning 37

Probabilistic Task Modelling for Meta-Learning

引用

37th Conference on Uncertainty in Artificial Intelligence, UAI 2021

作者： Nguyen, Cuong C. Do, Thanh-Toan Carneiro, Gustavo Australian Institute for Machine Learning University of Adelaide Australia Department of Data Science and AI Monash University Australia

We propose probabilistic task modelling - a generative probabilistic model for collections of tasks used in meta-learning. The proposed model combines variational auto-encoding and latent Dirichlet allocation to model each task as a mixture of Gaussian distribution in an embedding space. Such modelling provides an explicit representation of a task through its task-theme mixture. We present an efficient approximation inference technique based on variational inference method for empirical Bayes parameter estimation. We perform empirical evaluations to validate the task uncertainty and task distance produced by the proposed method through correlation diagrams of the prediction accuracy on testing tasks. We also carry out experiments of task selection in meta-learning to demonstrate how the task relatedness inferred from the proposed model help to facilitate meta-learning algorithms. © 2021 37th Conference on Uncertainty in Artificial Intelligence, UAI 2021. All Rights Reserved.

关键词： learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Mediguide:A machine learning based Smart Prescription System for Personalized Healthcare

Mediguide:A Machine Learning based Smart Prescription System...

引用

2025 International Conference on Artificial Intelligence and data Engineering, AIDE 2025

作者： Kumar K, Jeyaganesh Mithilesh, G. Monisha, K.M. Nandhini, S. Nithish Kumar, M. M.Kumarasamy College of Engineering Department of Artificial Intelligence and Data Science Karur India M.Kumarasamy College of Engineering Department of Artificial Intelligence and Machine Learning Karur India

ISBN: (纸本)9798331527518

This project uses a Decision Tree Classifier model which gives accurate health predictions based on the symptoms provided by users. The model has been trained at thousands of symptoms against diseases and thus predicts very accurately for the inputted data provided by the user. The system has an easy-to-use interface that helps users input their symptoms with ease and get instant predictions of potential diseases. In addition to predicting ailments, the application provides extensive information on the detected disease. Users are given a comprehensive breakdown of the disease, recommended medications, precautions, and personalized advice on diet and exercise regimes. It provides health insights that are meant to help users better manage their health and make better lifestyle decisions. With feedback loops, prediction accuracy and user experience can always be improved directly without worrying much about each setup. It seeks to use advanced technology to make practical health advice possible. Combining disease prediction in real time with meaningful health advice creates added value for users and encourages informed health choices. It enables users to own their health by providing them with a complete picture of their possible health problems and possible solutions to address them. This Project provides a powerful tool for more proactive users, with its combo of predictive analytics and health education resources.(And it helps us recognise the sport itself the user-friendly and detailed output that makes it easy and helpful for everyone to understand their health and what they can do about it.) It upskill traditionally trained AI learners to be perpendicular over ruinous health data towards an accessibly governed future, furnished with health facts and outcomes to improvement on the go. © 2025 IEEE.

关键词： Personalized medicine

来源：评论

学校读者我要写书评

暂无评论

CONVERGENCE ANALYSIS OF PROBABILITY FLOW ODE FOR SCORE-BASED GENERATIVE MODELS

arXiv

引用

arXiv 2024年

作者： Zhengyu Huang, Daniel Huang, Jiaoyang Lin, Zhengjiang Beijing International Center for Mathematical Research Center for Machine Learning Research Peking University Beijing China Department of Statistics and Data Science University of Pennsylvania PhiladelphiaPA United States Department of Mathematics Massachusetts Institute of Technology CambridgeMA United States

Score-based generative models have emerged as a powerful approach for sampling high-dimensional probability distributions. Despite their effectiveness, their theoretical underpinnings remain relatively underdeveloped. In this work, we study the convergence properties of deterministic samplers based on probability flow ODEs from both theoretical and numerical perspectives. Assuming access to L2-accurate estimates of the score function, we prove the total variation between the target and the generated data distributions can be bounded above by O(d3/4δ1/2) in the continuous time level, where d denotes the data dimension and δ represents the L2-score matching error. For practical implementations using a p-th order Runge-Kutta integrator with step size h, we establish error bounds of O(d3/4δ1/2 + d· (dh)p) at the discrete level. Finally, we present numerical studies on problems up to 128 dimensions to verify our theory. Copyright © 2024, The Authors. All rights reserved.

关键词： Distribution functions

来源：评论

学校读者我要写书评

暂无评论

The map equation goes neural: mapping network flows with graph neural networks 24

The map equation goes neural: mapping network flows with gra...

引用

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

作者： Christopher Blöcker Chester Tan Ingo Scholtes Data Analytics Group Department of Informatics University of Zurich Switzerland Chair of Machine Learning for Complex Networks Center for Artificial Intelligence and Data Science Julius-Maximilians-Universität Würzburg Germany

ISBN: (纸本)9798331314385

Community detection is an essential tool for unsupervised data exploration and revealing the organisational structure of networked systems. With a long history in network science, community detection typically relies on objective functions, optimised with custom-tailored search algorithms, but often without leveraging recent advances in deep learning. Recently, first works have started incorporating such objectives into loss functions for deep graph clustering and pooling. We consider the map equation, a popular information-theoretic objective function for unsupervised community detection, and express it in differentiable tensor form for optimisation through gradient descent. Our formulation turns the map equation compatible with any neural network architecture, enables end-to-end learning, incorporates node features, and chooses the optimal number of clusters automatically, all without requiring explicit regularisation. Applied to unsupervised graph clustering tasks, we achieve competitive performance against state-of-the-art deep graph clustering baselines in synthetic and real-world datasets.

关键词：

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：