Network Deconvolution
Network Deconvolution is a computational method that disentangles direct regulatory interactions from indirect correlations in inferred regulatory networks by mathematically removing transitive edge effects propagated through network paths.
50
Publications
12.7K
Citations
210
Authors
83
Institutions
Publications per year
2017–2026
31
Parents
50
Learning Deconvolution Network for Semantic Segmentation
Hyeonwoo Noh, Seunghoon Hong, Bohyung Han · 2015 · 4K citations
1–5 of 50
210
2
h-index
2
h-index
2
h-index
Pohang University of Science and Technology, South Korea
2 publications · 4.7K citations
2
h-index
2
h-index
1–5 of 210
83

Shanghai Jiao Tong University
Shanghai, China
4 h-index
11 publications
257 citations

Chinese Academy of Sciences
Beijing, China
4 h-index
10 publications
510 citations
Columbia University
New York, United States
3 h-index
17 publications
29.3K citations
University of Michigan
Ann Arbor, United States
3 h-index
4 publications
136 citations

Washington University in St. Louis
St Louis, United States
3 h-index
10 publications
450 citations
Cancer Genetics (United States)
Rutherford, United States
2 h-index
4 publications
9.7K citations
Center for Systems Biology
Boston, United States
2 h-index
6 publications
14.6K citations
Pohang University of Science and Technology
Pohang, South Korea
2 h-index
6 publications
13.9K citations
1–8 of 83
Repository · 5 publications · 707 citations
5
h-index
3 publications · 166 citations
3
h-index
2 publications · 88 citations
2
h-index
2 publications · 58 citations
2
h-index
2 publications · 57 citations
2
h-index
1–5