Published Articles >> Table of Contents >> Abstract

IEEE-INNS-ENNS International Joint Conference on Neural Networks (IJCNN'00)-Volume 4   p. 4083
Topographic ICA as a Model of V1 Receptive Fields
Aapo Hyvarinen, Helsinki University of Technology
Patrik Hoyer, Helsinki University of Technology
Mika Inki, Helsinki University of Technology

Full Article Text:

DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/IJCNN.2000.860754
Send link to a friend

Abstract
Independent component analysis (ICA), which is equivalent to linear sparse coding, has been recently used as a model of natural image statistics and V1 receptive fields. Olshausen and Field applied the principle of maximizing the sparseness of the coefficients of a linear representation to extract features from natural images. This leads to the emergence of oriented linear filters that have simultaneous localization in space and in frequency, thus resembling Gabor functions and V1 simple cell receptive fields. In this paper, we extend this model to explain emergence of V1 topography. Ordering the basis vectors so that vectors with strong higher-order correlations are near to each other does this. This is a new principle of topographic organization, and may be more relevant to natural image statistics than the more conventional topographic ordering based on Euclidean distances. For example, this topographic ordering leads to simultaneous emergence of complex cell properties: each neighborhood acts like a complex cell.
Back to Top Additional Information
Citation:  Aapo Hyvarinen, Patrik Hoyer, Mika Inki, "Topographic ICA as a Model of V1 Receptive Fields," ijcnn, p. 4083,  IEEE-INNS-ENNS International Joint Conference on Neural Networks (IJCNN'00)-Volume 4,  2000