Zobrazeno 1 - 10
of 79
pro vyhledávání: '"Michael Desmond"'
Autor:
Rajendra V.E Chilukuri, Viral K Patel, Marcia eMartinez, Jerry Charles Guyden, Michael Desmond Samms
Publikováno v:
Frontiers in Cell and Developmental Biology, Vol 2 (2014)
Stromal thymic epithelial cells with the multicellular structure unique to thymic nurse cells (TNCs) express the pH91 antigen on their cell surfaces. The multicellular TNC-complexes develop through an intimate association between αβTCR+CD4+CD8+ thy
Externí odkaz:
https://doaj.org/article/d0447338071f44969c3d18be424e7418
Autor:
Michelle Brachman, Zahra Ashktorab, Michael Desmond, Evelyn Duesterwald, Casey Dugan, Narendra Nath Joshi, Qian Pan, Aabhas Sharma
Publikováno v:
Proceedings of the ACM on Human-Computer Interaction. 6:1-27
Human data labeling with multiple labelers and the resulting conflict resolution remains the norm for many enterprise machine learning pipelines. Conflict resolution can be a time-intensive and costly process. Our goal was to study how human-AI colla
Publikováno v:
Open Forum Infectious Diseases. 9
Home infusion therapy is a rapidly growing field in healthcare, allowing patients to receive postacute care at home at a fraction of the cost of an inpatient stay. Understanding the various drug delivery systems can facilitate a more seamless dischar
Autor:
Michael Desmond, Michelle Brachman, Evelyn Duesterwald, Casey Dugan, Narendra Nath Joshi, Qian Pan, Carolina Spina
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 36:13161-13163
We demonstrate an AI assisted data labeling system which applies unsupervised and semi-supervised machine learning to facilitate accurate and efficient labeling of large data sets. Our system (1) applies representative data sampling and active learni
Autor:
Kristina Brimijoin, Zahra Ashktorab, Darrell C. Reimer, Michael Muller, Qian Pan, Josh Andres, Werner Geyer, Michael Desmond, Michelle Brachman, Evelyn Duesterwald, Aabhas Sharma, Casey Dugan, Narendra Nath Joshi, Christine T. Wolf
Publikováno v:
Proceedings of the ACM on Human-Computer Interaction. 5:1-27
Human labeling of training data is often a time-consuming, expensive part of machine learning. In this paper, we study "batch labeling", an AI-assisted UX paradigm, that aids data labelers by allowing a single labeling action to apply to multiple rec
Autor:
Qian Pan, Narendra Nath Joshi, Christine T. Wolf, Josh Andres, Michael Desmond, Aabhas Sharma, Evelyn Duesterwald, Casey Dugan, Michael Muller, Kristina Brimijoin, Zahra Ashktorab
Publikováno v:
CHI
Ground-truth labeling is an important activity in machine learning. Many studies have examined how crowdworkers apply labels to records in machine learning datasets. However, there have been few studies that have examined the work of domain experts w
Autor:
Kristina Brimijoin, Zahra Ashktorab, Michael Desmond, Aabhas Sharma, Qian Pan, Michael Muller, Catherine Finegan-Dollak, Casey Dugan, Narendra Nath Joshi, Evelyn Duesterwald, Michelle Brachman
Publikováno v:
26th International Conference on Intelligent User Interfaces.
Labeling data is an important step in the supervised machine learning lifecycle. It is a laborious human activity comprised of repeated decision making: the human labeler decides which of several potential labels to apply to each example. Prior work
Autor:
Ravi Gill, Peter William Collins, Margaret Rokicka, Hafiz Qureshi, Tim Nokes, Paul Diprose, Dale Watson, Augustine Tang, Martin Besser, Michael Desmond Creagh, Pratima Chowdary
Publikováno v:
Clinical and Applied Thrombosis/Hemostasis
A multicenter, retrospective, observational study of 4-factor prothrombin complex concentrate (PCC) and/or fresh frozen\ud plasma (FFP) use within routine clinical care unrelated to vitamin K antagonists was conducted. The PCC was administered\ud pre
Publikováno v:
Journal of VitreoRetinal Diseases. 3:54-56
Intravitreal antivascular endothelial growth factor (anti-VEGF) therapy is a standard of care for a variety of ophthalmological conditions. While the systemic use of these agents in oncology is well known to induce a number of renal-related adverse e