Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Dylan Cashman"'
Autor:
Ashley Suh, Mateus Espadoto, Gabriel Appleby, Remco Chang, Erik W. Anderson, Carlos Scheidegger, Mingwei Li, Dylan Cashman, Alexandru Telea
Publikováno v:
IEEE Transactions on Visualization and Computer Graphics. 29:1559-1572
Projection techniques are often used to visualize high-dimensional data, allowing users to better understand the overall structure of multi-dimensional spaces on a 2D screen. Although many such methods exist, comparably little work has been done on g
Presenting a predictive model's performance is a communication bottleneck that threatens collaborations between data scientists and subject matter experts. Accuracy and error metrics alone fail to tell the whole story of a model - its risks, strength
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::872a12790bcd0dfc5a38311de6029c59
http://arxiv.org/abs/2205.05749
http://arxiv.org/abs/2205.05749
Autor:
Raea Rasmussen, David E. Levari, Muna Akhtar, Chelsea S. Crittle, Megan Gately, Jeremy Pagan, Andrea Brennen, Dylan Cashman, Alia N. Wulff, Michael I. Norton, Samuel R. Sommers, Heather L. Urry
In a 2011 article in this journal entitled “Whites See Racism as a Zero-Sum Game That They Are Now Losing” ( Perspectives on Psychological Science, 6, 215–218), Norton and Sommers assessed Black and White Americans’ perceptions of anti-Black
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c3b90c204aa48329c71b62049244ec5a
https://doi.org/10.31234/osf.io/e6dar
https://doi.org/10.31234/osf.io/e6dar
Publikováno v:
2021 IEEE Workshop on Visual Analytics in Healthcare (VAHC).
Autor:
Dylan Cashman, Genevieve Patterson, Nathan Watts, Abigail Mosca, Remco Chang, Shannon Robinson
Publikováno v:
IEEE Computer Graphics and Applications. 38:39-50
We present RNNbow, an interactive tool for visualizing the gradient flow during backpropagation in training of recurrent neural networks. By visualizing the gradient, as opposed to activations, RNNbow offers insight into how the network is learning.
Autor:
Alex Endert, Shah Rukh Humayoun, Michael Gleicher, Florian Heimerl, Shenyu Xu, Remco Chang, Dylan Cashman, Cong Liu, Subhajit Das
Most visual analytics systems assume that all foraging for data happens before the analytics process; once analysis begins, the set of data attributes considered is fixed. Such separation of data construction from analysis precludes iteration that ca
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b445d3b2b573d0ae0757c57a56b7f919
http://arxiv.org/abs/2009.02865
http://arxiv.org/abs/2009.02865
Publikováno v:
IEEE transactions on visualization and computer graphics. 26(1)
The performance of deep learning models is dependent on the precise configuration of many layers and parameters. However, there are currently few systematic guidelines for how to configure a successful model. This means model builders often have to e
Publikováno v:
IEEE computer graphics and applications. 39(5)
Interactive model steering helps people incrementally build machine learning models that are tailored to their domain and task. Existing visual analytic tools allow people to steer a single model (e.g., assignment attribute weights used by a dimensio
Autor:
Abigail Mosca, Kendall Park, Subhajit Das, Shah Rukh Humayoun, John Thompson, Florian Heimerl, Michael Gleicher, John Stasko, Bahador Saket, Remco Chang, Alex Endert, Dylan Cashman
Many visual analytics systems allow users to interact with machine learning models towards the goals of data exploration and insight generation on a given dataset. However, in some situations, insights may be less important than the production of an
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e7029c367c16b97a8890600c7a036724
Publikováno v:
ICHI
This paper describes a principled statistical methodof preprocessing incidentally collected electronic medical recordsto facilitate short-term predictions of disease onset withoutexplicit interaction with patients (e.g., medical tests, questionnaires