Results 21 to 30 of about 10,455 (264)
A Biased Deep Tensor Factorization Network For Tensor Completion
CoRR, 2021 Tensor decomposition is a popular technique for tensor completion, However most of the existing methods are based on linear or shallow model, when the data tensor becomes large and the observation data is very small, it is prone to over fitting and the performance decreases significantly.
Qianxi Wu, An-Bao Xu
openaire +2 more sources
Tensor Completion Made Practical
CoRR, 2020 NeurIPS ...
Allen Liu, Ankur Moitra
openaire +4 more sources
Convex Coupled Matrix and Tensor Completion [PDF]
Neural Computation, 2018 We propose a set of convex low-rank inducing norms for coupled matrices and tensors (hereafter referred to as coupled tensors), in which information is shared between the matrices and tensors through common modes. More specifically, we first propose a mixture of the overlapped trace norm and the latent norms with the matrix trace norm, and then ...
Wimalawarne, Kishan +3 more
openaire +6 more sources
Low-Rank Tensor Completion by Sum of Tensor Nuclear Norm Minimization
IEEE Access, 2019 In this paper, we study the problem of low-rank tensor completion with the purpose of recovering a low-rank tensor from a tensor with partial observed items. To date, there are several different definitions of tensor ranks.
Yaru Su, Xiaohui Wu, Wenxi Liu
doaj +1 more source
Orthogonal random projection for tensor completion
IET Computer Vision, 2020 The low‐rank tensor completion problem, which aims to recover the missing data from partially observable data. However, most of the existing tensor completion algorithms based on Tucker decomposition cannot avoid using singular value decomposition (SVD ...
Yali Feng, Guoxu Zhou
doaj +1 more source
A Joint Tensor Completion and Prediction Scheme for Multi-Dimensional Spectrum Map Construction
IEEE Access, 2016 Spectrum data, which are usually characterized by many dimensions, such as location, frequency, time, and signal strength, present formidable challenges in terms of acquisition, processing, and visualization.
Mengyun Tang +4 more
doaj +1 more source
Contour information regularized tensor ring completion for realistic image restoration
IET Image Processing, 2022 Tensor completion has gained considerable research interest in recent years and has been frequently applied to image restoration. This type of method basically employs the low‐rank nature of images, implicitly requiring that the whole picture is of ...
Zhi Yu, Yihao Luo, Zhifa Liu, Guoxu Zhou
doaj +1 more source
Frontiers in Artificial Intelligence, 2022 A major challenge in many machine learning tasks is that the model expressive power depends on model size. Low-rank tensor methods are an efficient tool for handling the curse of dimensionality in many large-scale machine learning models.
Kaiqi Zhang, Cole Hawkins, Zheng Zhang
doaj +1 more source
Matrix completion and tensor rank [PDF]
Linear and Multilinear Algebra, 2015 In this paper, we show that the low rank matrix completion problem can be reduced to the problem of finding the rank of a certain tensor.
openaire +2 more sources
Tensor Completion Methods for Collaborative Intelligence
IEEE Access, 2020 In the race to bring Artificial Intelligence (AI) to the edge, collaborative intelligence has emerged as a promising way to lighten the computation load on edge devices that run applications based on Deep Neural Networks (DNNs).
Lior Bragilevsky, Ivan V. Bajic
doaj +1 more source