Results 61 to 70 of about 1,665,186 (233)
Efficient tensor decomposition-based filter pruning
Neural NetworksIn this paper, we present CORING, which is short for effiCient tensOr decomposition-based filteR prunING, a novel filter pruning methodology for neural networks. CORING is crafted to achieve efficient tensor decomposition-based pruning, a stark departure
Van Tien Pham +2 more
semanticscholar +1 more source
Hybrid Tensor Decomposition in Neural Network Compression [PDF]
Neural Networks, 2020 Deep neural networks (DNNs) have enabled impressive breakthroughs in various artificial intelligence (AI) applications recently due to its capability of learning high-level features from big data.
Bijiao Wu +4 more
semanticscholar +1 more source
Decomposition of Elasticity Tensor on Material Constants and Mesostructures of Metal Plates
CrystalsMost metal plates are orthorhombic aggregates of cubic crystallites. First, we discuss the representations of the stress tensor, the strain tensor, the elasticity tensor, and the rotation tensor under the Kelvin notation.
Genbao Liu +5 more
doaj +1 more source
A Hybrid Norm for Guaranteed Tensor Recovery
Frontiers in Physics, 2022 Benefiting from the superiority of tensor Singular Value Decomposition (t-SVD) in excavating low-rankness in the spectral domain over other tensor decompositions (like Tucker decomposition), t-SVD-based tensor learning has shown promising performance and
Yihao Luo +5 more
doaj +1 more source
Orthogonal tucker decomposition using factor priors for 2D+3D facial expression recognition
IET Biometrics, 2021 In this article, an effective approach is proposed to recognise the 2D+3D facial expression automatically based on orthogonal Tucker decomposition using factor priors (OTDFPFER).
Yunfang Fu +4 more
doaj +1 more source
Low rank tensor recovery via iterative hard thresholding
, 2016 We study extensions of compressive sensing and low rank matrix recovery (matrix completion) to the recovery of low rank tensors of higher order from a small number of linear measurements. While the theoretical understanding of low rank matrix recovery is
Rauhut, Holger +2 more
core +1 more source
Distributed large-scale tensor decomposition [PDF]
2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2014 Canonical Polyadic Decomposition (CPD), also known as PARAFAC, is a useful tool for tensor factorization. It has found application in several domains including signal processing and data mining. With the deluge of data faced in our societies, large-scale matrix and tensor factorizations become a crucial issue. Few works have been devoted to large-scale
de Almeida, André L. F. +1 more
openaire +2 more sources
The Tensor‐based Feature Analysis of Spatiotemporal Field Data With Heterogeneity
Earth and Space Science, 2020 Heterogeneity is an essential characteristic of the geographic phenomenon. However, most existing researches concerning heterogeneity are based on the matrix.
Dongshuang Li +5 more
doaj +1 more source
On the average condition number of tensor rank decompositions
, 2019 We compute the expected value of powers of the geometric condition number of random tensor rank decompositions. It is shown in particular that the expected value of the condition number of $n_1\times n_2 \times 2$ tensors with a random rank-$r ...
Breiding, Paul, Vannieuwenhoven, Nick
core +1 more source
A Constructive Algorithm for Decomposing a Tensor into a Finite Sum of Orthonormal Rank-1 Terms [PDF]
, 2015 We propose a constructive algorithm that decomposes an arbitrary real tensor into a finite sum of orthonormal rank-1 outer products. The algorithm, named TTr1SVD, works by converting the tensor into a tensor-train rank-1 (TTr1) series via the singular ...
Batselier, Kim, Liu, Haotian, Wong, Ngai
core +3 more sources