36,712 Hits in 4.4 sec

Estimating the unseen from multiple populations [article]

Aditi Raghunathan, Greg Valiant, James Zou
2017 arXiv   pre-print
We generalize this extrapolation and related unseen estimation problems to the multiple population setting, where population j has an unknown distribution D_j from which we observe n_j samples.  ...  This is an important and actively studied problem, with many applications ranging from unseen species estimation to genomics.  ...  In this paper, we address the general problem of estimating the unseen when we have samples from multiple populations, each corresponding to a potentially distinct distribution.  ... 
arXiv:1707.03854v1 fatcat:uccdbnpj7jeilhwkyvmeuwva6y

Estimation of clonal diversity in HTLV-1 infection

Daniel J Laydon, Anat Melamed, Aaron Sim, Nicolas A Gillet, Kathleen Sim, Sam Darko, J Kroll, Daniel C Douek, David A Price, Charles RM Bangham, Becca Asquith
2014 Retrovirology  
DivE can also be used to estimate with accuracy the population clone structure from small samples.  ...  Considering each clone as a "species", the question becomes analogous to the "unseen species problem" in population ecology.  ...  DivE can also be used to estimate with accuracy the population clone structure from small samples.  ... 
doi:10.1186/1742-4690-11-s1-o50 pmcid:PMC4044095 fatcat:3rdlpqlk4bcotl23e4eqf7tzum

Computation on shape manifold for atlas generation: application to whole heart segmentation of cardiac MRI

Xiahai Zhuang, Wenzhe Shi, Haiyan Wang, Daniel Rueckert, Sebastien Ourselin, Sebastien Ourselin, David R. Haynor
2013 Medical Imaging 2013: Image Processing  
By using image similarity metric to estimate the distance of shapes in the assumed manifold, we can estimate a close shape of an unseen image using Naderaya-Watson kernel regression function.  ...  The segmentation results on clinical data demonstrated an improved performance compared to existing methods, thanks to the usage of subject-specific atlases which had more similar shapes to the unseen  ...  shapes and use them to estimate the shape, T M1 , of the unseen image.  ... 
doi:10.1117/12.2007181 dblp:conf/miip/ZhuangSWRO13 fatcat:t2r7tdmujjd53eecohaxe2xjsa

Estimating T-cell repertoire diversity: limitations of classical estimators and a new approach

Daniel J. Laydon, Charles R. M. Bangham, Becca Asquith
2015 Philosophical Transactions of the Royal Society of London. Biological Sciences  
This is analogous to the 'unseen species problem' in ecology.  ...  We review the diversity (species richness) estimators that have been applied to T-cell repertoires and the methods used to validate these estimators.  ...  The original motivation for estimating diversity comes from population ecology, where the question of how many species there are in a given population gives rise to the 'unseen species problem': how many  ... 
doi:10.1098/rstb.2014.0291 pmid:26150657 pmcid:PMC4528489 fatcat:v42bxmaxfjfmbgwb2izkee4kpm

Quantitative prediction of integrase inhibitor resistance from genotype through consensus linear regression modeling

Koen Van der Borght, Ann Verheyen, Maxim Feyaerts, Liesbeth Van Wesenbeeck, Yvan Verlinden, Elke Van Craenenbroeck, Herman van Vlijmen
2013 Virology Journal  
The R 2 performance of this model on the clonal training data was 0.97, and 0.78 on an unseen population genotype-phenotype dataset of 171 clinical isolates from RAL treated and INI naïve patients.  ...  mutations to estimate INI resistance.  ...  Acknowledgements The authors would like to thank Kristel Van Laethem and Geert Verbeke for their valuable comments and suggestions to improve the manuscript.  ... 
doi:10.1186/1743-422x-10-8 pmid:23282253 pmcid:PMC3551713 fatcat:nmtzu7gfnfeklelxinfotjd45q

Multi-Agent Policy Transfer via Task Relationship Modeling [article]

Rongjun Qin, Feng Chen, Tonghan Wang, Lei Yuan, Xiaoran Wu, Zongzhang Zhang, Chongjie Zhang, Yang Yu
2022 arXiv   pre-print
We also find that fine-tuning the transferred policies help solve tasks that are hard to learn from scratch.  ...  We demonstrate that the task representation can capture the relationship among tasks, and can generalize to unseen tasks.  ...  Can our learning framework extract knowledge from multiple source tasks and transfer the cooperation knowledge to unseen tasks?  ... 
arXiv:2203.04482v1 fatcat:275ee4yegfcppgd7j22uvmfwfa

Probing Unseen Planet Populations with Resolved Debris Disk Structures [article]

Kate Su, Nick Ballering, Steve Ertel, Andras Gaspar, Grant Kennedy, David Leisawitz, Meredith MacGregor, Brenda Matthews, Amaya Moro-Martin, George Rieke, Jacob White, David Wilner, Mark Wyatt
2019 arXiv   pre-print
Resolved debris structures at multiple wavelengths and at all stages of evolution would reveal the properties of unseen planet populations, enabling a unique demographic study of overall planet formation  ...  Thousands of exoplanets have been found with many widely different from the ones in our own system.  ...  Resolved debris structures at multiple wavelengths and at all stages of evolution would reveal the properties of unseen planet populations, enabling a unique demographic study of overall planet formation  ... 
arXiv:1903.10616v1 fatcat:joqgfoliondalewxm5ihmukqhy

Estimating Hypervolume using Population Features from Dynamic Compartmental Models

Hugo Monzón Maldonado, Hernán Aguirre, Sébastien Verel, Arnaud Liefooghe, Bilel Derbel, Kiyoshi Tanaka
2021 Transaction of the Japanese Society for Evolutionary Computation  
We then introduce a model to estimate the hypervolume from the changes observed on non-dominated solutions in the population.  ...  We also show that the models produce good estimates on unseen instances of the same class of problems, and capture the variability of the algorithm when initialized with different populations.  ...  Furthermore, we show that the models produce good estimates on unseen instances, and are able to capture the variability of the algorithm when starting from different initial populations.  ... 
doi:10.11394/tjpnsec.12.12 fatcat:dhhh24c7offfra5yvzvsclkdsu

Debiased Batch Normalization via Gaussian Process for Generalizable Person Re-Identification [article]

Jiawei Liu, Zhipeng Huang, Liang Li, Kecheng Zheng, Zheng-Jun Zha
2022 arXiv   pre-print
Without access to the unseen domain, the feature statistics of the batch normalization (BN) layer learned from a limited number of source domains is doubtlessly biased for unseen domain.  ...  from source domains, and estimate more accurate Gaussian process by them in return, tending to real data distribution.  ...  Innovation Program of Anhui Province under Grants GXXT-2019-025, and the Fundamental Research Funds for the Central Universities under Grant WK2100000021.  ... 
arXiv:2203.01723v2 fatcat:hotc5igxmnee7k5thy4rzcbcjm

Adaptive Domain-Specific Normalization for Generalizable Person Re-Identification [article]

Jiawei Liu, Zhipeng Huang, Kecheng Zheng, Dong Liu, Xiaoyan Sun, Zheng-Jun Zha
2021 arXiv   pre-print
At the testing stage, AdsNorm projects images from unseen target domain into the same latent space, and adaptively integrates the domain-specific features carrying the source distributions by domain relevance  ...  Although existing person re-identification (Re-ID) methods have shown impressive accuracy, most of them usually suffer from poor generalization on unseen target domain.  ...  Domain Generalization General DG aims to improve the generalization of models on unseen target domain by training from multiple source domains.  ... 
arXiv:2105.03042v2 fatcat:e4ukjdtdnrh7faizuljzjx3fri

Inferring Unseen Components of the Internet Core

Brian Eriksson, Paul Barford, Joel Sommers, Robert Nowak
2011 IEEE Journal on Selected Areas in Communications  
For our data set, we show that our methods can predict the number of unseen routers to within a 13% error level, estimate 60% of the unseen distances between observed routers to within a one-hop error,  ...  Our work focuses on the discovery of the core of the Internet. We define "Internet core" as the set of routers that is roughly bounded by ingress/egress routers from stub autonomous systems.  ...  The components of our discovery methodology are: 1) Estimate the population size of unseen routers.  ... 
doi:10.1109/jsac.2011.111004 fatcat:5md45resq5cktdbywvghztuzr4

Robust inter-modality multi-atlas segmentation for PACS-based DTI quality control

Andrew J. Asman, Carolyn B. Lauzon, Bennett A. Landman, Maria Y. Law, William W. Boonn
2013 Medical Imaging 2013: Advanced PACS-based Imaging Informatics and Therapeutic Applications  
With the ever expanding scope of PACS archives -including multiple imaging modalities, multiple image types within a modality, and multi-site efforts, it is becoming increasingly burdensome to devise a  ...  To address the challenge of generalizing segmentations from one modality to another, we consider multi-atlas segmentation to transfer label information from labeled T1-weighted MRI data to unlabeled B  ...  This research was supported in part by a post-doctoral training grant in image science (T32 EB003817), the Vanderbilt CTSA (UL1 RR024975-01) from NCRR/NIH, and NIH/NINDS 1R21NS064534, 2R01EB006136, 1R03EB012461  ... 
doi:10.1117/12.2007587 pmid:24379940 pmcid:PMC3874255 fatcat:pt6w2wlxqbbyvkxowsm22oodoa

Manifold-constrained embeddings for the detection of white matter lesions in brain MRI

Samuel Kadoury, Guray Erus, Evangelia I. Zacharaki, Nikos Paragios, Christos Davatzikos
2012 2012 9th IEEE International Symposium on Biomedical Imaging (ISBI)  
The proposed method uses locally linear embedding (LLE) to create "normality" distributions in 12 locations of the brain where deviations from the manifolds are estimated by calculating geodesic distances  ...  A smooth mapping function approximating the relationship between ambient and manifold spaces as a joint distribution maps unseen test images in the intrinsic space.  ...  METHODS The computation of a distance between unseen image patches and a given population considered as a healthy distribution of periventricular areas, seen as a pathologic deviation from normality, consists  ... 
doi:10.1109/isbi.2012.6235610 pmid:24443675 pmcid:PMC3892901 dblp:conf/isbi/KadouryEZPD12 fatcat:c7ddzig57jcobpha2cp6piogvq

Applying Artificial Intelligence Methods for the Estimation of Disease Incidence: The Utility of Language Models

Yuanzhao Zhang, Robert Walecki, Joanne R. Winter, Felix J. S. Bragman, Sara Lourenco, Christopher Hart, Adam Baker, Yura Perov, Saurabh Johri
2020 Frontiers in Digital Health  
We found that, on average, BioBERT embeddings were the best for disease names across multiple tasks.  ...  The neural networks were trained and validated using data from the Global Burden of Disease study, and tested using independent data sourced from the epidemiological literature.Findings: A variety of language  ...  or population-level cohort and cross-sectional studies.  ... 
doi:10.3389/fdgth.2020.569261 pmid:34713043 pmcid:PMC8521977 fatcat:wwuwfodqrngnpnjuhavpt74mhy

Quantifying size and diversity of the human T cell alloresponse

Susan DeWolf, Boris Grinshpun, Thomas Savage, Sai Ping Lau, Aleksandar Obradovic, Brittany Shonts, Suxiao Yang, Heather Morris, Julien Zuber, Robert Winchester, Megan Sykes, Yufeng Shen
2018 JCI Insight  
Using these approaches, we measured the diversity and frequency of distinct alloreactive CD4+ and CD8+ T cell populations in HLA-mismatched responder-stimulator pairs.  ...  Alloreactive T lymphocytes are the primary mediators of immune responses in transplantation, both in the graft-versus-host and host-versus-graft directions.  ...  The content is solely the responsibility of the authors and does not necessarily represent the official views of the NIH.  ... 
doi:10.1172/jci.insight.121256 pmid:30089728 pmcid:PMC6129121 fatcat:xq74jhmf5vapbalqu6ztbfd46e
« Previous Showing results 1 — 15 out of 36,712 results