Learning Topographic Representations for Linearly Correlated Components

H. Sasaki, M.U. Gutmann, H. Shouno, A. Hyvärinen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

Recently, some variants of independent component analysis (ICA) have been proposed to estimate topographic representations. In these models, the assumptions of ICA are slightly relaxed: adjacent components are allowed to have higher order correlations while being linearly uncorrelated. In this paper, we propose a new statistical model for the estimation of topographic representations. In the proposed model, the estimated components are sparse and linearly correlated. To confirm the behavior of the model, we perform experiments on artificial data. In applications of the model to real data, we find emergence of a new kind of topographic representation for natural images and the outputs of simulated complex cells in the primary visual cortex.
Original languageEnglish
Title of host publicationWorkshop on Deep Learning and Unsupervised Feature Learning, NIPS
Number of pages9
Publication statusPublished - 2011


Dive into the research topics of 'Learning Topographic Representations for Linearly Correlated Components'. Together they form a unique fingerprint.

Cite this