Branding/Logomark minus Citation Combined Shape Icon/Bookmark-empty Icon/Copy Icon/Collection Icon/Close Copy 7 no author result Created with Sketch. Icon/Back Created with Sketch. Match!
Georgios B. Giannakis
University of Minnesota
1,272Publications
112H-index
51.3kCitations
Publications 1272
Newest
Published on Jun 1, 2019in IEEE Transactions on Signal Processing 4.20
Jia Chen3
Estimated H-index: 3
(UMN: University of Minnesota),
Gang Wang8
Estimated H-index: 8
(UMN: University of Minnesota),
Georgios B. Giannakis112
Estimated H-index: 112
(UMN: University of Minnesota)
Multiview canonical correlation analysis (MCCA) seeks latent low-dimensional representations encountered with multiview data of shared entities (a.k.a. common sources). However, existing MCCA approaches do not exploit the geometry of the common sources, which may be available a priori , or can be constructed using certain domain knowledge. This prior information about the common sources can be encoded by a graph, and be invoked as a regularizer to enrich the maximum variance MCCA framework. In t...
Source Cite
Published on May 1, 2019 in ICASSP (International Conference on Acoustics, Speech, and Signal Processing)
Jia Chen3
Estimated H-index: 3
(UMN: University of Minnesota),
Gang Wang8
Estimated H-index: 8
(UMN: University of Minnesota),
Georgios B. Giannakis112
Estimated H-index: 112
(UMN: University of Minnesota)
Source Cite
Published on May 1, 2019 in ICASSP (International Conference on Acoustics, Speech, and Signal Processing)
Fatemeh Sheikholeslami3
Estimated H-index: 3
(UMN: University of Minnesota),
Swayambhoo Jain5
Estimated H-index: 5
(UMN: University of Minnesota),
Georgios B. Giannakis112
Estimated H-index: 112
(UMN: University of Minnesota)
Source Cite
Published on May 1, 2019 in ICASSP (International Conference on Acoustics, Speech, and Signal Processing)
Liang Zhang4
Estimated H-index: 4
(UMN: University of Minnesota),
Gang Wang8
Estimated H-index: 8
(UMN: University of Minnesota),
Georgios B. Giannakis112
Estimated H-index: 112
(UMN: University of Minnesota)
Source Cite
Published on May 1, 2019in IEEE Transactions on Signal Processing 4.20
Gang Wang8
Estimated H-index: 8
(UMN: University of Minnesota),
Georgios B. Giannakis112
Estimated H-index: 112
(UMN: University of Minnesota),
JieCHEN27
Estimated H-index: 27
(BIT: Beijing Institute of Technology)
Neural networks with rectified linear unit (ReLU) activation functions (a.k.a. ReLU networks) have achieved great empirical success in various domains. Nonetheless, existing results for learning ReLU networks either pose assumptions on the underlying data distribution being, e.g., Gaussian, or require the network size and/or training size to be sufficiently large. In this context, the problem of learning a two-layer ReLU network is approached in a binary classification setting, where the data ar...
7 Citations Source Cite
12345678910