mtyka/laplossPublic NotificationsYou must be signed in to change notification settings Fork15 Star43 master BranchesTags Code Latest commit History 3 Commits LICENSE README.md laploss.py as described in this paper:https://arxiv.org/abs/1707.05776"Optimizing the Latent Space of Generative Networks...
fractional Laplacianwave equationsdispersionSeveral wave equations for power-law attenuation have a spatial fractional derivative in the loss term. Both one-sided and two-sided spatial fractional derivatives can give causal solutions and a phase velocity dispersion which satisfies the Kramers–Kronig ...
B.H. Sheng, D.H. Xiang, The performance of semi-supervised Laplacian regularized regression with least square loss, Int. J. Wavel. Multiresolut. Inf. Process. 15 (2) (2017) 31. 1750016.B. Sheng and D. Xiang, "The performance of semi-supervised Laplacian regularized regression with the...
The Laplacian eigenmaps (LE) is one of the most commonly used nonlinear dimensionality reduction methods and aims to find a low-dimensional representation to preserve the topological relationship between sample points in the original data. However, the 2-norm based loss function makes LE unable to ...
This study extends the twin support vector machine with the generalized pinball loss function (GPin-TSVM) into a semi-supervised framework by incorporating graph-based methods. The assumption is that connected data points should share similar labels, with mechanisms to handle noisy labels. Laplacian ...
frequency domain lossgenerative adversarial networkimage matchingimage processingLaplacian pyramidHao ChenSchool of Information Engineering Nantong Institute of Technology Nantong China Division of Information and Communication Convergence Engineering Mokwon Unive rsity Daejeon South KoreaXi Lu...
In this study, a k-nearest neighbor model based on multi-Laplacian and kernel risk sensitive loss was proposed, which introduces a kernel risk loss function derived from the K-local hyperplane distance nearest neighbor model as well as combining the Laplacian regularization method to...
The main purpose of this work is to propose the strategy to use the Laplacian smoothing stochastic gradient descent with combination of multiplicative angular margin to enhance the performance of angularly discriminative features of angular margin softmax loss for face recognition. The model is trained...