Generalizations of principal component analysis, optimization problems, and neural networks

By Juha Karhunen, Jyrki Joutsensalo. 1995

How researchers see this paper

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

Citations in the corpus

Deep learning in neural networks: An overview (2014, background): “…1995; Belouchrani, Abed-Meraim, Cardoso, & Moulines, 1997; Cardoso, 1994; Comon, 1994; Hyvärinen, Karhunen, & Oja, 2001; Jutten & Herault, 1991; Karhunen & Joutsensalo, 1995; Molgedey & Schuster, 1994; Schuster, 1992; Shan & Cottrell, 2014; Shan, Zhang, & Cottrell, 2007; Szabó, Póczos, &…”
Probabilistic independent component analysis for functional magnetic resonance imaging (2004, background): “Their approach has been further developed by [28] and [14].”
Neural networks for classification: a survey (2000, background): “Karhunen and Joutsensalo [89] have discussed many aspects of PCA performed by neural networks.”
Forecasting East Asian Indices Futures via a Novel Hybrid of Wavelet-PCA Denoising and Artificial Neural Network Models (2016, methodology): “The principal component analysis (PCA) technique, a competent feature extraction tool, is extensively applied in statistics, signal processing, and neural computing [51].”
Robust principal component analysis for computer vision (2001, background): “These reconstruction coefficients can be arbitrarily biased for an outlier.”
Lightweight Lossy Compression of Biometric Patterns via Denoising Autoencoders (2015, background): “In fact, [9], [10] showed that NNs perform a sort of non-linear PCA.”
A Framework for Robust Subspace Learning (2003, background): “…vision has received little attention, the problem has been studied in the statistics (Campbell, 1980; Huber, 1981; Jolliffe, 1986; Ruymagaart, 1981) and neural networks (Karhunen and Joutsensalo, 1995; Xu and Yuille, 1995; Yang and Wang, 1999) literature, and several algorithms have been proposed.”
PCA-SIFT: a more distinctive representation for local image descriptors (2004, background): “While PCA suffers from a number of shortcomings [ 8 , 10], such as its implicit assumption of Gaussian distributions and its restriction to orthogonal linear combinations, it remains popular due to its simplicity.”