Handwritten digit classification using higher order singular value decomposition

DOI10.1016/j.patcog.2006.08.004zbMath1119.68188OpenAlexW2060225944MaRDI QIDQ856465

Lars Eldén, Berkant Savas

Publication date: 7 December 2006

Published in: Pattern Recognition (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.patcog.2006.08.004

zbMATH Keywords

least squarestensorshigher order singular value decompositiontensor approximationhandwritten digit classification

Mathematics Subject Classification ID

Pattern recognition, speech recognition (68T10)

Related Items (23)

Efficient alternating least squares algorithms for low multilinear rank approximation of tensors ⋮ Spatio-temporal Koopman decomposition ⋮ Optimization landscape of Tucker decomposition ⋮ Low rank tensor recovery via iterative hard thresholding ⋮ Tensor-train decomposition for image recognition ⋮ Structured multi-way arrays and their applications ⋮ Krylov-type methods for tensor computations.I ⋮ Randomized algorithms for the computation of multilinear rank-\((\mu_1,\mu_2,\mu_3)\) approximations ⋮ Tensor Approximation for Multidimensional and Multivariate Data ⋮ The Computation of Low Multilinear Rank Approximations of Tensors via Power Scheme and Random Projection ⋮ Unnamed Item ⋮ Randomized algorithms for the low multilinear rank approximations of tensors ⋮ Factorization strategies for third-order tensors ⋮ The tensor rank problem over the quaternions ⋮ Nonlinearly Preconditioned Optimization on Grassmann Manifolds for Computing Approximate Tucker Tensor Decompositions ⋮ An efficient randomized algorithm for computing the approximate Tucker decomposition ⋮ Flip-flop spectrum-revealing QR factorization and its applications to singular value decomposition ⋮ HOID: Higher Order Interpolatory Decomposition for Tensors Based on Tucker Representation ⋮ The rank of a 2 × 2 × 2 tensor ⋮ Unfoldings and the rank-one approximation of the tensor ⋮ Decomposition for a quaternion tensor triplet with applications ⋮ A Krylov-Schur-like method for computing the best rank-\((r_1,r_2,r_3)\) approximation of large and sparse tensors ⋮ On the Uniqueness and Perturbation to the Best Rank-One Approximation of a Tensor

Cites Work

• Pattern recognition by means of disjoint principal components models
• Algorithm 862
• A Multilinear Singular Value Decomposition
• On the Best Rank-1 and Rank-(R₁ ,R₂ ,. . .,R_N) Approximation of Higher-Order Tensors
• The elements of statistical learning. Data mining, inference, and prediction
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: Handwritten digit classification using higher order singular value decomposition