Emily J King

Dr. Emily J King

orcid

Research Focus & Metrics

Academic Career Length

18Years (2009-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 February 2013 in Journal of Mathematical Imaging and Vision
Verified
Journal Article
Closed access
PDF file
EKEmily J King
Emily J King
GKGitta Kutyniok
Gitta Kutyniok
Xiaosheng ZhuangXiaosheng Zhuang
Xiaosheng Zhuang

1 October 2018 in Linear Algebra and its Applications
Verified
Journal Article
Closed access
MFMatthew Fickus
Matthew Fickus
JJJohn Jasper
John Jasper
EKEmily J King
Emily J King
DMDustin G. Mixon
Dustin G. Mixon

22 February 2016 in Experiments in Fluids
Verified
Journal Article
Closed access
PDF file
RRRafael Reisenhofer
Rafael Reisenhofer
Johannes KieferJohannes Kiefer
Johannes Kiefer
EKEmily J King
Emily J King

5 November 2019 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
SDSoren Dittmer
Soren Dittmer
EKEmily J King
Emily J King
PMPeter Maass
Peter Maass
Despite their prevalence in neural networks, we still lack a thorough theoretical characterization of rectified linear unit (ReLU) layers. This article aims to further our understanding of ReLU layers by studying how the activation function ReLU interacts with the linear component of the layer and what role this interaction plays in the success of the neural network in achieving its intended task. To this end, we introduce two new tools: ReLU singular values of operators and the Gaussian mean width of operators. By presenting, on the one hand, theoretical justifications, results, and interpretations of these two concepts and, on the other hand, numerical experiments and results of the ReLU singular values and the Gaussian mean width being applied to trained neural networks, we hope to give a comprehensive, singular-value-centric view of ReLU layers. We find that ReLU singular values and the Gaussian mean width do not only enable theoretical insights but also provide one with metrics that seem promising for practical applications. In particular, these measures can be used to distinguish correctly and incorrectly classified data as it traverses the network. We conclude by introducing two tools based on our findings: double layers and harmonic pruning.

1 January 2019 in SIAM Journal on Discrete Mathematics
Verified
Journal Article
Closed access
EKEmily J King
Emily J King
XTXiaoxian Tang
Xiaoxian Tang
We derive a procedure for computing an upper bound on the number of equiangular lines in various Euclidean vector spaces by generalizing the classical pillar decomposition developed by Lemmens and ...

1 May 2021 in Neural Networks
Verified
Journal Article
Closed access
SMScott Mahan
Scott Mahan
EKEmily J King
Emily J King
ACAlex Cloninger
Alex Cloninger