Generalized Autoencoder: A Neural Network Framework for Dimensionality Reduction

By Yan Huang, Yizhou Wang, Liang Wang. 2014

398 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Relational autoencoder for feature extraction (2017, background): “[24] proposed a Generalized Autoencoder (GAE) targeting at reconstructing the data relationships instead of the data features.”
Dimensionality reduction strategy based on auto-encoder (2015, background): “Some researchers dedicated to investigating several fundamental issues of neural networks with one or two hidden layer [10] [11] [14] [7] [12] [13].”
Autoencoding the retrieval relevance of medical images (2015, methodology): “Another method is the gray level correlogram which is supposed to extract both gray-level and spatial information from an image [14].”
Auto-encoder based dimensionality reduction (2016, background): “Some researchers committed themselves to investigating several fundamental issues of neural networks with one or two hidden layers [8] [1] [22] [23] [3] [9] [17] [25] [21] [27].”
Research on denoising sparse autoencoder (2016, methodology): “Autoencoder has not only got the attention of theorists, but also been widely applied to practice for solving machine learning tasks [8–12].”
Learning in high-dimensional multimedia data: the state of the art (2015, methodology): “In GAE [93], they extend the traditional autoencoder and propose a dimensionality reduction method by manifold learning, which iteratively explores data relation and uses the relation to pursue the manifold structure.”
scGNN is a novel graph neural network framework for single-cell RNA-Seq analyses (2021, methodology): “Some limitations can still be found in scGNN. (i) It is prone to achieve better results with large data sets, compared to relatively small data sets (e.g., 1000 cells), as it is designed to learn better representations with many cells from scRNA-Seq data, as shown in the benchmark results, and (ii)”
Deep Feature Learning for EEG Recordings (2015, background): “This strategy can be considered as a special case of the generalized framework for auto-encoders proposed by Wang et al. (2014).”
Text Classification Algorithms: A Survey (2019, methodology): “k that is trained to attempt to copy its input to its output [91]. The autoencoder has achieved great success as a dimensionality reduction method via the powerful reprehensibility of neural networks [92]. The ﬁrst version of autoencoder was introduced Information 2019, 10, 150 17 of 68 by D.E. Rume”
A review of machine learning in processing remote sensing data for mineral exploration (2021, neutral): “data and reconstruct it accurately (Wang et al., 2014).”