Topographic Product Models Applied to Natural Scene Statistics

DOI10.1162/089976606775093936zbMath1095.68648OpenAlexW2142615865WikidataQ51957397 ScholiaQ51957397MaRDI QIDQ5473188

Simon Osindero, Max Welling, Geoffrey E. Hinton

Publication date: 19 June 2006

Published in: Neural Computation (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1162/089976606775093936

zbMATH Keywords

independent components analysisGaussian scale mixture models

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Neural networks for/in biological studies, artificial life and related topics (92B20) Machine vision and scene understanding (68T45)

Related Items (10)

A Two-Layer Model of Natural Stimuli Estimated with Score Matching ⋮ Correlated topographic analysis: estimating an ordering of correlated components ⋮ Independent component analysis: recent advances ⋮ Unifying Blind Separation and Clustering for Resting-State EEG/MEG Functional Connectivity Analysis ⋮ Learning Visual Spatial Pooling by Strong PCA Dimension Reduction ⋮ Simultaneous Estimation of Nongaussian Components and Their Correlation Structure ⋮ Foveated nonlocal self-similarity ⋮ Receptive Field Self-Organization in a Model of the Fine Structure in V1 Cortical Columns ⋮ Soft Mixer Assignment in a Hierarchical Generative Model of Natural Scene Statistics ⋮ A Maximum-Likelihood Interpretation for Slow Feature Analysis

Cites Work

• Topographic Independent Component Analysis
• Training Products of Experts by Minimizing Contrastive Divergence
• Image denoising using scale mixtures of gaussians in the wavelet domain
• Independent component analysis applied to feature extraction from colour and stereo images
• 10.1162/jmlr.2003.4.7-8.1235
• A Hierarchical Bayesian Model for Learning Nonlinear Statistical Regularities in Nonstationary Natural Signals

This page was built for publication: Topographic Product Models Applied to Natural Scene Statistics