Results 61 to 70 of about 201,485 (174)

Learning Invariant Riemannian Geometric Representations Using Deep Nets

, 2017
Non-Euclidean constraints are inherent in many kinds of data in computer vision and machine learning, typically as a result of specific invariance requirements that need to be respected during high-level inference.
Lohit, Suhas, Turaga, Pavan
core   +1 more source

Semi-Supervised Manifold Alignment Using Parallel Deep Autoencoders

Algorithms, 2019
The aim of manifold learning is to extract low-dimensional manifolds from high-dimensional data. Manifold alignment is a variant of manifold learning that uses two or more datasets that are assumed to represent different high-dimensional representations ...
Fayeem Aziz, Aaron S. W. Wong, Stephan Chalup   +2 more
doaj   +1 more source

Neural manifold under plasticity in a goal driven learning behaviour.

PLoS Computational Biology, 2021
Neural activity is often low dimensional and dominated by only a few prominent neural covariation patterns. It has been hypothesised that these covariation patterns could form the building blocks used for fast and flexible motor control.
Barbara Feulner, Claudia Clopath
doaj   +1 more source

A Geometric Perspective on Functional Outlier Detection

Stats, 2021
We consider functional outlier detection from a geometric perspective, specifically: for functional datasets drawn from a functional manifold, which is defined by the data’s modes of variation in shape, translation, and phase.
Moritz Herrmann, Fabian Scheipl
doaj   +1 more source

Probability Distribution-Based Dimensionality Reduction on Riemannian Manifold of SPD Matrices

IEEE Access, 2020
Representing images and videos with Symmetric Positive Definite (SPD) matrices and utilizing the intrinsic Riemannian geometry of the resulting manifold has proved successful in many computer vision tasks.
Jieyi Ren, Xiao-Jun Wu
doaj   +1 more source

Learning 3-manifold triangulations

Journal of Physics A: Mathematical and Theoretical
Abstract Real 3-manifold triangulations can be uniquely represented by isomorphism signatures. Databases of these isomorphism signatures are generated for a variety of 3-manifolds and knot complements, using SnapPy and Regina, then these language-like inputs are used to train various machine learning architectures to differentiate the ...
Costantino, F, He, Y, Heyes, E, Hirst, E
openaire   +3 more sources

Simplicial Nonlinear Principal Component Analysis [PDF]

, 2012
We present a new manifold learning algorithm that takes a set of data points lying on or near a lower dimensional manifold as input, possibly with noise, and outputs a simplicial complex that fits the data and the manifold.
Hunt, Thomas, Krener, Arthur J.
core   +1 more source

Manifold Constrained Low-Rank and Joint Sparse Learning for Dynamic Cardiac MRI

IEEE Access, 2020
Reconstruction from highly accelerated dynamic magnetic resonance imaging (MRI) is of great significance for medical diagnosis. The application of low-rank and sparse matrix decomposition to MRI can improve imaging speed and efficiency.
Qingmin Meng, Xianchao Xiu, Yan Li
doaj   +1 more source

Application of Wavelet Packet Entropy Flow Manifold Learning in Bearing Factory Inspection Using the Ultrasonic Technique

Sensors, 2014
For decades, bearing factory quality evaluation has been a key problem and the methods used are always static tests. This paper investigates the use of piezoelectric ultrasonic transducers (PUT) as dynamic diagnostic tools and a relevant signal ...
Xiaoguang Chen, Dan Liu, Guanghua Xu, Kuosheng Jiang, Lin Liang   +4 more
doaj   +1 more source

Local non‐linear alignment for non‐linear dimensionality reduction

IET Computer Vision, 2017
In manifold learning, alignment is performed with the objective of deriving the global low‐dimensional coordinates of input data from their local coordinates.
Guo Niu, Zhengming Ma
doaj   +1 more source