Auto-association by multilayer perceptrons and singular value decomposition

DOI10.1007/BF00332918zbMath0651.92006OpenAlexW2017257315WikidataQ28292671 ScholiaQ28292671MaRDI QIDQ1106762

Y. Kamp, Hervé Bourlard

Publication date: 1988

Published in: Biological Cybernetics (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/bf00332918

zbMATH Keywords

neural networkssingular value decompositiondata compressionmultilayer perceptrondimensionality reductioninformation processinglow rank matrix approximationauto-associationnonlinearities of the hidden units

Mathematics Subject Classification ID

Artificial intelligence (68T99) Other natural sciences (mathematical treatment) (92F05) Physiological, cellular and medical topics (92Cxx)

Related Items (30)

A comprehensive deep learning-based approach to reduced order modeling of nonlinear time-dependent parametrized PDEs ⋮ Forward Stepwise Deep Autoencoder-Based Monotone Nonlinear Dimensionality Reduction Methods ⋮ A comparative investigation on model selection in independent factor analysis ⋮ Autoencoders reloaded ⋮ Justifying and Generalizing Contrastive Divergence ⋮ Autoencoder asset pricing models ⋮ Solvable models of layered neural networks based on their differential structure ⋮ Linearly Constrained Nonsmooth Optimization for Training Autoencoders ⋮ Preserving differential privacy in deep neural networks with relevance-based adaptive noise imposition ⋮ Surrogate modeling for high dimensional uncertainty propagation via deep kernel polynomial chaos expansion ⋮ Boosting neural network feature extraction by reduced accuracy activation functions ⋮ Deep nonparametric estimation of intrinsic data structures by chart autoencoders: generalization error and robustness ⋮ Complex-valued autoencoders ⋮ An Introduction to Neural Data Compression ⋮ Sim2vec: node similarity preserving network embedding ⋮ Reduced-order deep learning for flow dynamics. The interplay between deep learning and model reduction ⋮ A CNN-based shock detection method in flow visualization ⋮ Deep Learning with Periodic Features and Applications in Particle Physics ⋮ Processing simple geometric attributes with autoencoders ⋮ Unnamed Item ⋮ Thermodynamics of restricted Boltzmann machines and related learning dynamics ⋮ Non-iterative and fast deep learning: multilayer extreme learning machines ⋮ Component models for fuzzy data ⋮ Unnamed Item ⋮ A comparison of three methods for principal component analysis of fuzzy interval data ⋮ Unnamed Item ⋮ Multilevel Artificial Neural Network Training for Spatially Correlated Learning ⋮ Feedforward neural networks for principal components extraction. ⋮ Unsupervised learning in neural computation. ⋮ Edge-backpropagation for noisy logo recognition

Cites Work

• Least squares, singular values and matrix approximations
• Updating the singular value decomposition
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: Auto-association by multilayer perceptrons and singular value decomposition