- Title
- Semi-supervised manifold alignment using parallel deep autoencoders
- Creator
- Aziz, Fayeem; Wong, Aaron S. W.; Chalup, Stephan
- Relation
- ARC.LE160100002 http://purl.org/au-research/grants/arc/LE160100002
- Relation
- Algorithms Vol. 12, Issue 9, no. 186
- Publisher Link
- http://dx.doi.org/10.3390/a12090186
- Publisher
- MDPI AG
- Resource Type
- journal article
- Date
- 2019
- Description
- 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 of the same underlying manifold. Manifold alignment can be successful in detecting latent manifolds in cases where one version of the data alone is not sufficient to extract and establish a stable low-dimensional representation. The present study proposes a parallel deep autoencoder neural network architecture for manifold alignment and conducts a series of experiments using a protein-folding benchmark dataset and a suite of new datasets generated by simulating double-pendulum dynamics with underlying manifolds of dimensions 2, 3 and 4. The dimensionality and topological complexity of these latent manifolds are above those occurring in most previous studies. Our experimental results demonstrate that the parallel deep autoencoder performs in most cases better than the tested traditional methods of semi-supervised manifold alignment. We also show that the parallel deep autoencoder can process datasets of different input domains by aligning the manifolds extracted from kinematics parameters with those obtained from corresponding image data.
- Subject
- deep autoencoder; dimensionality reduction; manifold learning; 3-manifold; machine learning; manifold alignment; autoencoder; deep neural network; deep learning; double pendulum
- Identifier
- http://hdl.handle.net/1959.13/1456133
- Identifier
- uon:45184
- Identifier
- ISSN:1999-4893
- Rights
- © 2019 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
- Language
- eng
- Full Text
- Reviewed
- Hits: 1355
- Visitors: 1448
- Downloads: 106
Thumbnail | File | Description | Size | Format | |||
---|---|---|---|---|---|---|---|
View Details Download | ATTACHMENT02 | Publisher version (open access) | 13 MB | Adobe Acrobat PDF | View Details Download |