Soft Mixer Assignment in a Hierarchical Generative Model of Natural Scene Statistics

DOI10.1162/NECO.2006.18.11.2680MaRDI QIDQ3413086zbMATHOpenAlexWikidataFDO

Authors Odelia Schwartz, Terrence J. Sejnowski, Peter Dayan

Publication date 3 January 2007

Published in Neural Computation (Search for Journal in Brave)

Full work available at URL http://europepmc.org/articles/pmc2915771

Mathematics Subject Classification ID

General biostatistics (92B15) Signal theory (characterization, reconstruction, filtering, etc.) (94A12) Image analysis in multivariate analysis (62H35) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08)

Recommendations

• Topographic Product Models Applied to Natural Scene Statistics
• A Two-Layer Model of Natural Stimuli Estimated with Score Matching
• scientific article; zbMATH DE number 1820166
• The Student-\(t\) mixture as a natural image patch prior with application to image compression
• Recognition in Hierarchical Models

Cites work

• A Hierarchical Bayesian Model for Learning Nonlinear Statistical Regularities in Nonstationary Natural Signals
• A Mathematical Theory of Communication
• Image denoising using scale mixtures of gaussians in the wavelet domain
• Neocognition: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position
• Random cascades on wavelet trees and their use in analyzing and modeling natural images
• Slow Feature Analysis: Unsupervised Learning of Invariances
• Topographic Product Models Applied to Natural Scene Statistics

Cited in

(6)

• Integrating flexible normalization into midlevel representations of deep convolutional neural networks
• Topographic Product Models Applied to Natural Scene Statistics
• Learning nonlinear statistical regularities in natural images by modeling the outer product of image intensities
• Local non-linear interactions in the visual cortex may reflect global decorrelation
• Dependency reduction with divisive normalization: justification and effectiveness
• Predictive Coding and the Slowness Principle: An Information-Theoretic Approach

This page was built for publication: Soft Mixer Assignment in a Hierarchical Generative Model of Natural Scene Statistics

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3413086)