The role of neural network activation functions
A wide variety of activation functions have been proposed for neural networks. The Rectified
Linear Unit (ReLU) is especially popular today. There are many practical reasons that …
Linear Unit (ReLU) is especially popular today. There are many practical reasons that …
[HTML][HTML] Current-based bearing fault diagnosis using deep learning algorithms
AS Barcelos, AJM Cardoso - Energies, 2021 - mdpi.com
Artificial intelligence algorithms and vibration signature monitoring are recurrent approaches
to perform early bearing damage identification in induction motors. This approach is …
to perform early bearing damage identification in induction motors. This approach is …
Continuous-Domain Signal Reconstruction Using -Norm Regularization
We focus on the generalized-interpolation problem. There, one reconstructs continuous-
domain signals that honor discrete data constraints. This problem is infinite-dimensional and …
domain signals that honor discrete data constraints. This problem is infinite-dimensional and …
TV-based reconstruction of periodic functions
We introduce a general framework for the reconstruction of periodic multivariate functions
from finitely many and possibly noisy linear measurements. The reconstruction task is …
from finitely many and possibly noisy linear measurements. The reconstruction task is …
[HTML][HTML] Sparsest piecewise-linear regression of one-dimensional data
We study the problem of one-dimensional regression of data points with total-variation (TV)
regularization (in the sense of measures) on the second derivative, which is known to …
regularization (in the sense of measures) on the second derivative, which is known to …
Delaunay-triangulation-based learning with Hessian total-variation regularization
Regression is one of the core problems tackled in supervised learning. Neural networks with
rectified linear units generate continuous and piecewise-linear (CPWL) mappings and are …
rectified linear units generate continuous and piecewise-linear (CPWL) mappings and are …
Coupled splines for sparse curve fitting
We formulate as an inverse problem the construction of sparse parametric continuous curve
models that fit a sequence of contour points. Our prior is incorporated as a regularization …
models that fit a sequence of contour points. Our prior is incorporated as a regularization …
Explicit representations for Banach subspaces of Lizorkin distributions
S Neumayer, M Unser - Analysis and Applications, 2023 - infoscience.epfl.ch
The Lizorkin space is well suited to the study of operators like fractional Laplacians and the
Radon transform. In this paper, we show that the space is unfortunately not complemented in …
Radon transform. In this paper, we show that the space is unfortunately not complemented in …
Hybrid-spline dictionaries for continuous-domain inverse problems
We study one-dimensional continuous-domain inverse problems with multiple generalized
total-variation regularization, which involves the joint use of several regularization operators …
total-variation regularization, which involves the joint use of several regularization operators …
[PDF][PDF] Sparsest continuous piecewise-linear representation of data
We study the problem of interpolating one-dimensional data with total variation
regularization on the second derivative, which is known to promote piecewise-linear …
regularization on the second derivative, which is known to promote piecewise-linear …