Principal Component Neural Networks: Theory and Applications

By K. Diamantaras, Sun-Yuan Kung. 1996

Subfields: Representation & Self-Supervised Learning, Model Architectures

How researchers see this paper

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

In Representation & Self-Supervised Learning

1. Jianfeng Gao
2. Bernhard Schölkopf
3. Xiaodong Liu
4. Alex Smola
5. Xiaodong He
6. Li Deng
7. Kevin Duh
8. Fernando De la Torre

In Model Architectures

1. Fernando De la Torre
2. José Carlos Príncipe
3. Xiaodong He
4. Li Deng
5. K. Müller
6. Bernhard Schölkopf
7. Deniz Erdoğmuş
8. Kevin Duh

Citations in the corpus

• Representation Learning Using Multi-Task Deep Neural Networks for Semantic Classification and Information Retrieval (2015, background): “, 1990), ESA (Gabrilovich and Markovitch, 2007), PCA (Karhunen, 1998), and non-linear kernel variants (Schölkopf et al.”
• Information Theoretic Learning (2005, background): “Recall that maximization of output variance is basically principal component analysis (PCA) for which there are known on-line and local algorithms [10], [27].”
• Why Do Similarity Matching Objectives Lead to Hebbian/Anti-Hebbian Networks? (2017, background): “ outputs principal components (scores) rather than principal eigenvectors of the input covariance (loadings). Such difference in formulation is motivated by our interest in PSP or PCA neural networks (Diamantaras and Kung, 1996) that output principal components, yt, rather than principal eigenvectors”
• A Framework for Robust Subspace Learning (2003, methodology): “Observe, that with standard PCA, this ratio can be calculated in terms of eigenvalues of the covariance matrix (Diamantaras, 1996).”
• Nonlinear Component Analysis as a Kernel Eigenvalue Problem (1998, methodology): “Rather than giving a full review of this field here, we briefly describe five approaches and refer readers to Diamantaras and Kung (1996) for more details.”