Natural image statistics. A probabilistic approach to early computational vision.

From MaRDI portal
Publication:1019002

DOI10.1007/978-1-84882-491-1zbMath1178.68622OpenAlexW104847522MaRDI QIDQ1019002

Jarmo Hurri, Patrik O. Hoyer, Aapo Hyvärinen

Publication date: 27 May 2009

Published in: Computational Imaging and Vision (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/978-1-84882-491-1




Related Items (34)

A Two-Layer Model of Natural Stimuli Estimated with Score MatchingIDC Breast Cancer Detection Using Deep Learning SchemesHierarchical linear dynamical systems for unsupervised musical note recognitionIndependent component analysis based on information bottleneckSparse Coding on the Spot: Spontaneous Retinal Waves Suffice for Orientation SelectivityCorrelated topographic analysis: estimating an ordering of correlated componentsHow to compare noisy patches? patch similarity beyond Gaussian noiseSlowdown of BCM plasticity with many synapsesFlexibly regularized mixture models and application to image segmentationIdentifiability of latent-variable and structural-equation models: from linear to nonlinearRejoinder to: ``Identifiability of latent-variable and structural-equation models: from linear to nonlinearWeight dependence in BCM leads to adjustable synaptic competitionA computational model for grid maps in neural populationsInput Statistics and Hebbian Cross-Talk EffectsLearning Nonlinear Statistical Regularities in Natural Images by Modeling the Outer Product of Image IntensitiesTopological Sparse Learning of Dynamic Form PatternsA Hebbian/Anti-Hebbian Neural Network for Linear Subspace Learning: A Derivation from Multidimensional Scaling of Streaming DataLearning Slowness in a Sparse Model of Invariant Feature DetectionOrthogonal Connectivity Factorization: Interpretable Decomposition of Variability in Correlation MatricesLearning Visual Spatial Pooling by Strong PCA Dimension ReductionThe Two-Dimensional Gabor Function Adapted to Natural Image Statistics: A Model of Simple-Cell Receptive Fields and Sparse Structure in ImagesSimultaneous Estimation of Nongaussian Components and Their Correlation StructureSparseness, Antisparseness and Anything in Between: The Operating Point of a Neuron Determines Its Computational RepertoireAutomated multi-class brain tumor types detection by extracting Rica based features and employing machine learning techniquesMultiple Timescale Online Learning Rules for Information Maximization with Energetic ConstraintsLearning Midlevel Auditory Codes from Natural Sound StatisticsAnalysis and performance of CMA blind deconvolution for image restorationFrom Riemannian trichromacy to quantum color opponency via hyperbolicitySpatio-chromatic information available from different neural layers via gaussianizationEfficient dictionary learning with sparseness-enforcing projectionsA computational theory of visual receptive fieldsIntegrating Flexible Normalization into Midlevel Representations of Deep Convolutional Neural NetworksUnnamed ItemUnnamed Item


Uses Software



This page was built for publication: Natural image statistics. A probabilistic approach to early computational vision.