Topographic Product Models Applied to Natural Scene Statistics

DOI10.1162/089976606775093936zbMath1095.68648WikidataQ51957397 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 analysis; Gaussian scale mixture models

Mathematics Subject Classification ID

68T05: Learning and adaptive systems in artificial intelligence

92B20: Neural networks for/in biological studies, artificial life and related topics

68T45: Machine vision and scene understanding

Related Items

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, Correlated topographic analysis: estimating an ordering of correlated components, Foveated nonlocal self-similarity, Independent component analysis: recent advances, A Two-Layer Model of Natural Stimuli Estimated with Score Matching, 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

• Unnamed Item
• Topographic Independent Component Analysis
• Training Products of Experts by Minimizing Contrastive Divergence
• Image denoising using scale mixtures of gaussians in the wavelet domain
• 10.1162/jmlr.2003.4.7-8.1235
• A Hierarchical Bayesian Model for Learning Nonlinear Statistical Regularities in Nonstationary Natural Signals