Auto-encoder based dimensionality reduction

By Yasi Wang, Hongxun Yao, Sicheng Zhao. Neurocomputing, 2016

930 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/9e98010a840d549ad657829f78006ce7578525f7

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

A Survey on Deep Learning for Multimodal Data Fusion (2020, methodology): “The SAE has been widely used in many fields, including dimension reduction (Wang, Yao, & Zhao, 2016), image recognition (Jia, Shao, Li, Zhao, & Fu, 2018), and text classification (Chen & Zaki, 2017).”
Recent Advances of Hyperspectral Imaging Technology and Applications in Agriculture (2020, methodology): “[154] proposed an auto‐encoder‐based dimensionality reduction method that is a deep learning‐based approach.”
A Comprehensive Overview and Comparative Analysis on Deep Learning Models: CNN, RNN, LSTM, GRU (2023, neutral): “unsupervised learning tasks, such as generative modeling [54], dimensionality reduction [55], feature extraction [56], anomaly or outlier detection [57], and denoising [58].”
A Deep Learning Approach to Network Intrusion Detection (2018, result): “Most researchers [8]–[10] use auto-encoders as a non-linear transformation to discover interesting data structures, by imposing other constraints on the network, and compare the results with those of PCA (linear transformation).”
Machine Learning and Integrative Analysis of Biomedical Big Data (2019, background): “Autoencoder, a building block of many deep learning networks, can also be employed for nonlinear FE by restricting the number of hidden layer nodes to less than the number of original input nodes [38,39].”
Artificial intelligence in recommender systems (2020, background): “Autoencoders(AE)[34]areunsupervisedneuralnetworks for learning feature representations where the purpose is dimensionality reduction, data compression, or data denois-123 ing.”
State Representation Learning for Control: An Overview (2018, methodology): “Auto-encoders (AE) are a common tool used to learn state representations that are widely used for dimensionality reduction [ Hinton et al., 2006, Wang et al., 2012, Wang et al., 2016].”
The Application of Deep Learning in Cancer Prognosis Prediction (2020, methodology): “In recent years, deep learning has been applied to biomedical research to annotate pathogenicity of genetic variants [51,52], show state-of-the-art performance in the task of genomic variant calling [53] and improve protein folding prediction [54,55].”