English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  A Model for Learning Topographically Organized Parts-Based Representations of Objects in Visual Cortex: Topographic Nonnegative Matrix Factorization

Hosoda, K., Watanabe, M., Wersing, H., Koerner, E., Tsujino, H., Tamura, H., et al. (2009). A Model for Learning Topographically Organized Parts-Based Representations of Objects in Visual Cortex: Topographic Nonnegative Matrix Factorization. Neural computation, 21(9), 2605-2633. doi:10.1162/neco.2009.03-08-722.

Item is

Basic

show hide
Item Permalink: http://hdl.handle.net/11858/00-001M-0000-0013-C2D6-6 Version Permalink: http://hdl.handle.net/21.11116/0000-0002-BE14-2
Genre: Journal Article

Files

show Files

Locators

show

Creators

show
hide
 Creators:
Hosoda, K, Author
Watanabe, M1, Author              
Wersing, H, Author
Koerner, E, Author
Tsujino, H, Author
Tamura, H, Author
Fujita, I, Author
Affiliations:
1External Organizations, ou_persistent22              

Content

show
hide
Free keywords: -
 Abstract: Object representation in the inferior temporal cortex (IT), an area of visual cortex critical for object recognition in the primate, exhibits two prominent properties: (1) objects are represented by the combined activity of columnar clusters of neurons, with each cluster representing component features or parts of objects, and (2) closely related features are continuously represented along the tangential direction of individual columnar clusters. Here we propose a learning model that reflects these properties of parts-based representation and topographic organization in a unified framework. This model is based on a nonnegative matrix factorization (NMF) basis decomposition method. NMF alone provides a parts-based representation where nonnegative inputs are approximated by additive combinations of nonnegative basis functions. Our proposed model of topographic NMF (TNMF) incorporates neighborhood connections between NMF basis functions arranged on a topographic map and attains the topographic property without losing the parts-based property of the NMF. The TNMF represents an input by multiple activity peaks to describe diverse information, whereas conventional topographic models, such as the self-organizing map (SOM), represent an input by a single activity peak in a topographic map. We demonstrate the parts-based and topographic properties of the TNMF by constructing a hierarchical model for object recognition where the TNMF is at the top tier for learning high-level object features. The TNMF showed better generalization performance over NMF for a data set of continuous view change of an image and more robustly preserving the continuity of the view change in its object representation. Comparison of the outputs of our model with actual neural responses recorded in the IT indicates that the TNMF reconstructs the neuronal responses better than the SOM, giving plausibility to the parts-based learning of the model.

Details

show
hide
Language(s):
 Dates: 2009-09
 Publication Status: Published in print
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Method: -
 Identifiers: DOI: 10.1162/neco.2009.03-08-722
BibTex Citekey: 5812
 Degree: -

Event

show

Legal Case

show

Project information

show

Source 1

show
hide
Title: Neural computation
Source Genre: Journal
 Creator(s):
Affiliations:
Publ. Info: Cambridge, Mass. : MIT Press
Pages: - Volume / Issue: 21 (9) Sequence Number: - Start / End Page: 2605 - 2633 Identifier: ISSN: 0899-7667
CoNE: https://pure.mpg.de/cone/journals/resource/954925561591