Search Results for author:
Found 10 papers, 2 papers with code
Blind Image Denoising and Inpainting Using Robust Hadamard Autoencoders
Herein we demonstrate these techniques on standard machine learning tasks, such as image inpainting and denoising for the MNIST and CIFAR10 datasets.
A Nonlinear Dimensionality Reduction Framework Using Smooth Geodesics
Herein, we propose a framework for nonlinear dimensionality reduction that generates a manifold in terms of smooth geodesics that is designed to treat problems in which manifold measurements are either sparse or corrupted by noise.
Dimension Estimation Using Autoencoders
In DE, one attempts to estimate the intrinsic dimensionality or number of latent variables in a set of measurements of a random vector.
Bounded Manifold Completion
Nonlinear dimensionality reduction or, equivalently, the approximation of high-dimensional data using a low-dimensional nonlinear manifold is an active area of research.
A Patch-based Image Denoising Method Using Eigenvectors of the Geodesics' Gramian Matrix
Thus, here we propose a novel and computationally efficient image denoising method that is capable of producing accurate images.
Machine Learning in LiDAR 3D point clouds
For instance, we observe that combining feature engineering with a dimension reduction a method such as PCA, there is an improvement in the accuracy of the classification with respect to doing a straightforward classification with the raw data.
A Pre-training Oracle for Predicting Distances in Social Networks
OSP can be easily extended to other domains such as random networks by choosing an appropriate model to generate synthetic training data, and therefore promises to impact many different network learning problems.
Reconstruction of Fragmented Trajectories of Collective Motion using Hadamard Deep Autoencoders
Learning dynamics of collectively moving agents such as fish or humans is an active field in research.
Graph Coordinates and Conventional Neural Networks -- An Alternative for Graph Neural Networks
We propose Topology Coordinate Neural Network (TCNN) and Directional Virtual Coordinate Neural Network (DVCNN) as novel and efficient alternatives to message passing GNNs, that directly leverage the graph's topology, sidestepping the computational challenges presented by competing algorithms.
Rethinking the Relationship between Recurrent and Non-Recurrent Neural Networks: A Study in Sparsity
In particular, RNNs are known to be Turing complete, and therefore capable of representing any computable function (such as any other types of NNs), but herein we argue that the relationship runs deeper and is more practical than this.
