Tensor rank learning in CP decomposition via convolutional neural network
Authors:
- Mingyi ZhouMZMingyi Zhou
- Yipeng LiuYLYipeng Liu
- Zhen LongZLZhen Long
- Longxi ChenLCLongxi Chen
- Ce ZhuCZCe Zhu
- 1 April 2019
- journal article
- research article
- Published by Elsevier in Signal Processing: Image Communication
- Vol. 73, 12-21
Abstract
No abstract availableKeywords
Funding Information
- National Natural Science Foundation of China (61602091, 61571102)
- Belarusian Republican Foundation for Fundamental Research (ZYGX2016J199, ZYGX2014Z003)
This publication has 21 references indexed in Scilit:
- Tensor Decompositions for Signal Processing Applications: From two-way to multiway component analysisIEEE Signal Processing Magazine, 2015
- Bayesian CP Factorization of Incomplete Tensors with Automatic Rank DeterminationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- Most Tensor Problems Are NP-HardJournal of the ACM, 2013
- Multi-structural Signal Recovery for Biomedical Compressive SensingIEEE Transactions on Biomedical Engineering, 2013
- The density-matrix renormalization group in the age of matrix product statesAnnals of Physics, 2011
- Tensor Decompositions and ApplicationsSIAM Review, 2009
- Face recognition: a convolutional neural-network approachIEEE Transactions on Neural Networks, 1997
- Tensor rank is NP-completeJournal of Algorithms, 1990
- Three-way arrays: rank and uniqueness of trilinear decompositions, with application to arithmetic complexity and statisticsLinear Algebra and its Applications, 1977
- Some Mathematical Notes on Three-Mode Factor AnalysisPsychometrika, 1966