Zobrazeno 1 - 10
of 24 306
pro vyhledávání: '"Regularization (mathematics)"'
Publikováno v:
IEEE Transactions on Neural Networks and Learning Systems. 34:2451-2465
Tensor-ring (TR) decomposition was recently studied and applied for low-rank tensor completion due to its powerful representation ability of high-order tensors. However, most of the existing TR-based methods tend to suffer from deterioration when the
Publikováno v:
Big Data. 11:59-70
To deal with a large amount of redundant data in the indirect category database and inefficient redundancy elimination of the existing methods, we proposed an indirect category data transfer learning algorithm based on regularization discrimination.
Publikováno v:
IEEE Transactions on Evolutionary Computation. 27:37-51
Due to the unavoidable influence of sparse and Gaussian noise during the process of data acquisition, the quality of hyperspectral images (HSIs) is degraded and their applications are greatly limited. It is therefore necessary to restore clean HSIs.
Publikováno v:
IEEE Transactions on Neural Networks and Learning Systems. 34:157-170
Passenger-flow anomaly detection and prediction are essential tasks for intelligent operation of the metro system. Accurate passenger-flow representation is the foundation of them. However, spatiotemporal dependencies, complex dynamic changes, and an
Autor:
Sören Bartels, Nico Weber
Publikováno v:
Mathematical Control and Related Fields. 13:35-62
In this paper, we focus on learning optimal parameters for PDE-based image denoising and decomposition models. First, we learn the regularization parameter and the differential operator for gray-scale image denoising using the fractional Laplacian in
Publikováno v:
IEEE Transactions on Multimedia. 25:126-139
Domain generalization aims to generalize a network trained on multiple domains to unknown yet related domains. Operating under the assumption that invariant information generalizes well to unknown domains, previous work has aimed to minimize the disc
Publikováno v:
IEEE Transactions on Neural Networks and Learning Systems. 33:7717-7727
Most modern learning problems are highly overparameterized, i.e., have many more model parameters than the number of training data points. As a result, the training loss may have infinitely many global minima (parameter vectors that perfectly ``inter
Publikováno v:
IEEE Transactions on Knowledge and Data Engineering. 34:5840-5853
Publikováno v:
IEEE Transactions on Cybernetics. 52:12734-12744
Multiview subspace clustering (MVSC) leverages the complementary information among different views of multiview data and seeks a consensus subspace clustering result better than that using any individual view. Though proved effective in some cases, e
Publikováno v:
Mathematics of Operations Research. 47:3239-3260
Entropy regularization has been extensively adopted to improve the efficiency, the stability, and the convergence of algorithms in reinforcement learning. This paper analyzes both quantitatively and qualitatively the impact of entropy regularization