检索结果-内蒙古大学图书馆

Multi-Task learning for Sparsity Pattern Heterogeneity: Statistical and Computational Perspectives

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Behdin, Kayhan Loewinger, Gabriel Kishida, Kenneth T. Parmigiani, Giovanni Mazumder, Rahul MIT Operations Research Center CambridgeMA United States Machine Learning Team National Institute on Mental Health BethesdaMD United States Department of Physiology and Pharmacology Department of Neurosurgery Wake Forest School of Medicine Winston SalemNC United States Department of Biostatistics Harvard School of Public Health BostonMA United States Department of Data Science Dana Farber Cancer Institute BostonMA United States MIT Sloan Schools of Management CambridgeMA United States

We consider a problem in Multi-Task learning (MTL) where multiple linear models are jointly trained on a collection of datasets ("tasks"). A key novelty of our framework is that it allows the sparsity pattern of regression coefficients and the values of non-zero coefficients to differ across tasks while still leveraging partially shared structure. Our methods encourage models to share information across tasks through separately encouraging 1) coefficient supports, and/or 2) nonzero coefficient values to be similar. This allows models to borrow strength during variable selection even when non-zero coefficient values differ across tasks. We propose a novel mixed-integer programming formulation for our estimator. We develop custom scalable algorithms based on block coordinate descent and combinatorial local search to obtain high-quality (approximate) solutions for our estimator. Additionally, we propose a novel exact optimization algorithm to obtain globally optimal solutions. We investigate the theoretical properties of our estimators. We formally show how our estimators leverage the shared support information across tasks to achieve better variable selection performance. We evaluate the performance of our methods in simulations and two biomedical applications. Our proposed approaches appear to outperform other sparse MTL methods in variable selection and prediction accuracy. We provide the sMTL package on CRAN. Copyright © 2022, The Authors. All rights reserved.

关键词： Linearization

Improving Cardiovascular Disease Prediction With machine learning Using Mental Health data: A Prospective UK Biobank Study

学校读者我要写书评

暂无评论

JACC: Advances

JACC: Advances 2024年第9期3卷 101180-101180页

作者： Dorraki, Mohsen Liao, Zhibin Abbott, Derek Psaltis, Peter J. Baker, Emma Bidargaddi, Niranjan Wardill, Hannah R. van den Hengel, Anton Narula, Jagat Verjans, Johan W. School of Computer and Mathematical Sciences The University of Adelaide Adelaide Australia Australian Institute for Machine Learning (AIML) Adelaide Australia Lifelong Health Theme South Australian Health and Medical Research Institute (SAHMRI) Adelaide Australia School of Electrical & Electronic Engineering University of Adelaide Adelaide Australia Faculty of Health and Medical Sciences The University of Adelaide Adelaide Australia Department of Cardiology Central Adelaide Local Health Network Adelaide Australia College of Medicine and Public Health Flinders University Adelaide Australia Precision Cancer Medicine Theme South Australian Health and Medical Research Institute (SAHMRI) Adelaide Australia School of Biomedicine Faculty of Health and Medical Sciences University of Adelaide Adelaide Australia University of Texas Health Science Center Houston United States

Background: Robust and accurate prediction of cardiovascular disease (CVD) risk facilitates early intervention to benefit patients. The intricate relationship between mental health disorders and CVD is widely recognized. However, existing models often overlook psychological factors, relying on a limited set of clinical and lifestyle parameters, or being developed on restricted population subsets. Objectives: This study aims to assess the impact of integrating psychological data into a novel machine learning (ML) approach on enhancing CVD prediction performance. Methods: Using a comprehensive UK Biobank data set (n = 375,145), the correlation between CVD and traditional and psychological risk factors was examined. CVD included hypertensive disease, ischemic heart disease, heart failure, and arrhythmias. An ensemble ML model containing 5 constituent algorithms (decision tree, random forest, XGBoost, support vector machine, and deep neural network) was tested for its ability to predict CVD based on 2 training data sets: using traditional CVD risk factors alone, or using a combination of traditional and psychological risk factors. Results: A total of 375,145 subjects with normal health status and with CVD were included. The ensemble ML model could predict CVD with 71.31% accuracy using traditional CVD risk factors alone. However, by adding psychological factors to the training data, accuracy increased to 85.13%. The accuracy and robustness of the ensemble ML model outperformed all 5 constituent learning algorithms. Conclusions: Incorporating mental health assessment data within an ensemble ML model results in a significantly improved, highly accurate, CVD prediction model, outperforming traditional risk factor prediction alone. © 2024 The Authors

关键词： artificial intelligence cardiovascular disease cardiovascular prediction machine learning mental health

Brain Imaging Generation with Latent Diffusion Models

学校读者我要写书评

暂无评论

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

T-Cell Receptor Optimization with Reinforcement learning and Mutation Policies for Precision Immunotherapy

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Chen, Ziqi Min, Martin Renqiang Guo, Hongyu Cheng, Chao Clancy, Trevor Ning, Xia Computer Science and Engineering The Ohio State University ColumbusOH43210 United States Machine Learning Department NEC Labs PrincetonNJ08540 United States Digital Technologies Research Centre National Research Council Canada ON Canada Department of Medicine Baylor College of Medicine HoustonTX77030 United States NEC Oncolmmunity AS Oslo Cancer Cluster Innovation Park Ullernchausséen 64 Oslo0379 Norway Biomedical Informatics The Ohio State University ColumbusOH43210 United States Translational Data Analytics Institute The Ohio State University ColumbusOH43210 United States

T cells monitor the health status of cells by identifying foreign peptides displayed on their surface. T-cell receptors (TCRs), which are protein complexes found on the surface of T cells, are able to bind to these peptides. This process is known as TCR recognition and constitutes a key step for immune response. Optimizing TCR sequences for TCR recognition represents a fundamental step towards the development of personalized treatments to trigger immune responses killing cancerous or virus-infected cells. In this paper, we formulated the search for these optimized TCRs as a reinforcement learning (RL) problem, and presented a framework TCRPPO with a mutation policy using proximal policy optimization. TCRPPO mutates TCRs into effective ones that can recognize given peptides. TCRPPO leverages a reward function that combines the likelihoods of mutated sequences being valid TCRs measured by a new scoring function based on deep autoencoders, with the probabilities of mutated sequences recognizing peptides from a peptide-TCR interaction predictor. We compared TCRPPO with multiple baseline methods and demonstrated that TCRPPO significantly outperforms all the baseline methods to generate positive binding and valid TCRs. These results demonstrate the potential of TCRPPO for both precision immunotherapy and peptide-recognizing TCR motif discovery. © 2023, CC BY.

关键词： Reinforcement learning

Correction: Multivariate clustering for maximizing the small cell users’ performance based on the dynamic interference alignment

学校读者我要写书评

暂无评论

Wireless Networks 2023年第1期30卷 593-593页

作者： Dakshinamoorthy, Prabakar Vaitilingam, Saminadan Sundar, Ramesh Department of Data Science and Business Systems School of Computing College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur India Department of Electronics and Communication Engineering Puducherry Technological University Puducherry India Department of Artificial Intelligence and Machine Learning Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai India

OC07.03: Automated cortical analysis from third-dimensional second trimester ultrasound scans

学校读者我要写书评

暂无评论

Ultrasound in Obstetrics & Gynecology 2024年第S1期64卷 18-18页

作者： M.K. Wyburd I. Consortium M. Jenkinson A. Namburete Computer Science University of Oxford Oxford United Kingdom University of Oxford Nuffield Department of Women's and Reproductive Health Oxford United Kingdom Wellcome Centre for Integrative Neuroimaging FMRIB University of Oxford Oxford United Kingdom Australian Institute for Machine Learning School of Computer and Mathematical Sciences University of Adelaide Adelaide SA Australia

Toward a 'Standard Model' of machine learning

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Hu, Zhiting Xing, Eric P. Halıcıoğlu Data Science Institute University of California San Diego San Diego United States Machine Learning Department Carnegie Mellon University Pittsburgh United States Mohamed bin Zayed University of Artificial Intelligence Abu Dhabi United Arab Emirates Petuum Inc. Pittsburgh United States

machine learning (ML) is about computational methods that enable machines to learn concepts from experience. In handling a wide variety of experience ranging from data instances, knowledge, constraints, to rewards, adversaries, and lifelong interaction in an ever-growing spectrum of tasks, contemporary ML/AI (artificial intelligence) research has resulted in a multitude of learning paradigms and methodologies. Despite the continual progresses on all different fronts, the disparate narrowly focused methods also make standardized, composable, and reusable development of ML approaches difficult, and preclude the opportunity to build AI agents that panoramically learn from all types of experience. This article presents a standardized ML formalism, in particular a 'standard equation' of the learning objective, that offers a unifying understanding of many important ML algorithms in the supervised, unsupervised, knowledge-constrained, reinforcement, adversarial, and online learning paradigms, respectively-those diverse algorithms are encompassed as special cases due to different choices of modeling components. The framework also provides guidance for mechanical design of new ML approaches and serves as a promising vehicle toward panoramic machine learning with all experience. © 2021, CC BY.

关键词： learning algorithms

Adversarial learning with Cost-Sensitive Classes

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Shen, Haojing Chen, Sihong Wang, Ran Wang, Xizhao Big Data Institute College of Computer Science and Software Engineering Guangdong Key Lab. of Intelligent Information Processing Shenzhen University Guangdong Shenzhen518060 China The College of Mathematics and Statistics Shenzhen University Shenzhen518060 China The Shenzhen Key Laboratory of Advanced Machine Learning and Applications Shenzhen University Shenzhen518060 China

It is necessary to improve the performance of some special classes or to particularly protect them from attacks in adversarial learning. This paper proposes a framework combining cost-sensitive classification and adversarial learning together to train a model that can distinguish between protected and unprotected classes, such that the protected classes are less vulnerable to adversarial examples. We find in this framework an interesting phenomenon during the training of deep neural networks, called Min-Max property, that is, the absolute values of most parameters in the convolutional layer approach zero while the absolute values of a few parameters are significantly larger becoming bigger. Based on this Min-Max property which is formulated and analyzed in a view of random distribution, we further build a new defense model against adversarial examples for adversarial robustness improvement. An advantage of the built model is that it performs better than the standard one and can combine with adversarial training to achieve an improved performance. It is experimentally confirmed that, regarding the average accuracy of all classes, our model is almost as same as the existing models when an attack does not occur and is better than the existing models when an attack occurs. Specifically, regarding the accuracy of protected classes, the proposed model is much better than the existing models when an attack occurs. © 2021, CC BY.

关键词： Deep neural networks

Comparative performance analysis of the resnet backbones of mask RCNN to segment the signs of COVID-19 in chest CT scans

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Aleem, Muhammad Raj, Rahul Khan, Arshad Ghulam Ishaq Khan Institute of Engineering Sciences and Technology Topi KPK 23640 Pakistan Independent Researcher Machine Learning in NLP and Computer Vision Data Science professional Southampton United Kingdom

COVID-19 has been detrimental in terms of the number of fatalities and rising number of critical patients across the world. According to the UNDP (United National Development Programme) Socio-Economic programme, aimed at the COVID-19 crisis, the pandemic is far more than a health crisis: it is affecting societies and economies at their core 2. There has been greater developments recently in the chest X-ray-based imaging technique as part of the COVID-19 diagnosis especially using Convolution Neural Networks (CNN) for recognising and classifying images. However, given the limitation of supervised labelled imaging data, the classification and predictive risk modelling of medical diagnosis tend to compromise. This paper aims to identify and monitor the effects of COVID-19 on the human lungs by employing Deep Neural Networks on axial CT (Chest Computed Tomography) scan of lungs. We have adopted Mask RCNN, with ResNet50 and ResNet101 as its backbone, to segment the regions, affected by COVID-19 coronavirus. Using the regions of human lungs, where symptoms have manifested, the model classifies condition of the patient as either "Mild" or "Alarming". Moreover, the model is deployed on the Google Cloud Platform (GCP) to simulate the online usage of the model for performance evaluation and accuracy improvement. The ResNet101 backbone model produces an F1 score of 0.85 and faster prediction scores with an average time of 9.04 seconds per inference. Copyright © 2020, The Authors. All rights reserved.

关键词： Computer aided diagnosis