scispace - formally typeset
Search or ask a question
Institution

National Research University – Higher School of Economics

EducationMoscow, Russia
About: National Research University – Higher School of Economics is a education organization based out in Moscow, Russia. It is known for research contribution in the topics: Population & Politics. The organization has 12873 authors who have published 23376 publications receiving 256396 citations.


Papers
More filters
Journal ArticleDOI
TL;DR: In this article, the authors quantified maternal mortality throughout the world by underlying cause and age from 1990 to 2015 for ages 10-54 years by systematically compiling and processing all available data sources from 186 of 195 countries and territories.

641 citations

Journal ArticleDOI
TL;DR: An amendment to this paper has been published and can be accessed via a link at the top of the paper.
Abstract: An amendment to this paper has been published and can be accessed via a link at the top of the paper.

617 citations

Journal ArticleDOI
Haidong Wang1, Zulfiqar A Bhutta2, Zulfiqar A Bhutta3, Matthew M Coates1  +610 moreInstitutions (263)
TL;DR: The Global Burden of Disease 2015 Study provides an analytical framework to comprehensively assess trends for under-5 mortality, age-specific and cause-specific mortality among children under 5 years, and stillbirths by geography over time and decomposed the changes in under- 5 mortality to changes in SDI at the global level.

591 citations

Posted Content
TL;DR: This paper converts the dense weight matrices of the fully-connected layers to the Tensor Train format such that the number of parameters is reduced by a huge factor and at the same time the expressive power of the layer is preserved.
Abstract: Deep neural networks currently demonstrate state-of-the-art performance in several domains. At the same time, models of this class are very demanding in terms of computational resources. In particular, a large amount of memory is required by commonly used fully-connected layers, making it hard to use the models on low-end devices and stopping the further increase of the model size. In this paper we convert the dense weight matrices of the fully-connected layers to the Tensor Train format such that the number of parameters is reduced by a huge factor and at the same time the expressive power of the layer is preserved. In particular, for the Very Deep VGG networks we report the compression factor of the dense weight matrix of a fully-connected layer up to 200000 times leading to the compression factor of the whole network up to 7 times.

588 citations


Authors

Showing all 13307 results

NameH-indexPapersCitations
Rasmus Nielsen13555684898
Matthew Jones125116196909
Fedor Ratnikov123110467091
Kenneth J. Arrow113411111221
Wil M. P. van der Aalst10872542429
Peter Schmidt10563861822
Roel Aaij98107144234
John W. Berry9735152470
Federico Alessio96105442300
Denis Derkach96118445772
Marco Adinolfi9583140777
Michael Alexander9588138749
Alexey Boldyrev9443932000
Shalom H. Schwartz9422067609
Richard Blundell9348761730
Network Information
Related Institutions (5)
Saint Petersburg State University
53.4K papers, 1.1M citations

88% related

Moscow State University
123.3K papers, 1.7M citations

88% related

Russian Academy of Sciences
417.5K papers, 4.5M citations

84% related

Carnegie Mellon University
104.3K papers, 5.9M citations

83% related

École Polytechnique
39.2K papers, 1.2M citations

82% related

Performance
Metrics
No. of papers from the Institution in previous years
YearPapers
2023129
2022584
20212,477
20203,025
20192,589
20182,259