Principal component neural networks — Theory and applications

By Juha Karhunen. 1998

Subfields: Representation & Self-Supervised Learning

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. Xiaodong Liu
3. Xiaodong He
4. Jimeng Sun
5. Kevin Duh
6. Li Deng
7. Christos Faloutsos
8. J. Cadima

Citations in the corpus

• Representation Learning Using Multi-Task Deep Neural Networks for Semantic Classification and Information Retrieval (2015, methodology): “Traditional techniques include LSA (Deerwester et al., 1990), ESA (Gabrilovich and Markovitch, 2007), PCA (Karhunen, 1998), and non-linear kernel variants (Schölkopf et al., 1998).”
• Independent component analysis of Gabor features for face recognition (2003, methodology): “Principal component analysis [ 7 ] is the method of choice when the primary goal is to project the similarity judgment for face recognition into a low dimensional space [45].”
• Information processing, dimensionality reduction and reinforcement learning in the basal ganglia. (2003, methodology): “The model devised by Kung and Diamantaras (and an earlier model (Rubner and Tavan, 1989; Rubner and Schulten, 1990)) uses hierarchical lateral connectivity between the output layer neurons (Kung and Diamantaras, 1990; Diamantaras and Kung, 1996) in which neuron i is connected to neurons i + 1 throug”
• Gabor-based kernel PCA with fractional power polynomial models for face recognition (2004, unknown): “While the Hebbian networks, the replicator networks, and the principal curves are all capable of implementing nonlinearPCA, kernel PCAenjoys simple implementation by means of kernel functions [15], [43].”
• Streaming Pattern Discovery in Multiple Time-Series (2005, methodology): “We experimented with several alternatives [30, 15] and found this particular method to have the best properties for our setting: it is very efficient in terms of computational and memory requirements, while converging quickly, with no special parameters to tune.”
• A Hebbian/Anti-Hebbian Neural Network for Linear Subspace Learning: A Derivation from Multidimensional Scaling of Streaming Data (2015, methodology): “We refer to (Becker and Plumbley, 1996; Diamantaras and Kung, 1996; Diamantaras, 2002) for a detailed review of these and further developments.”
• Principal component analysis: a review and recent developments (2016, background): “Substantial books have been written on the subject [3,4] and there are even whole books on variants of PCA for special types of data [5,6].”
• Principal Component Analysis in ECG Signal Processing (2007, background): “This property can be illustrated by the two-sample data vector x = [x(1) x(2)]T = [cos(φ) sin(φ)]T , being completely defined by the uniformly distributed angle φ [24].”
• Hebbian Learning based Orthogonal Projection for Continual Learning of Spiking Neural Networks (2024, methodology): “Several methods extend original Oja’s rule to top k principal components (Oja, 1989; Diamantaras & Kung, 1996; Pehlevan et al., 2015), and we focus on the subspace algorithm that updates weights as ∆ H = η yx ⊤ − yy ⊤ H , which enables weights to converge to a dominant principal sub-space (Yan et…”
• Ultradense Word Embeddings by Orthogonal Transformation (2016, methodology): “For PCA, the performance is relatively stable until the subspace becomes smaller than 100 .”