CUED Publications database

On sparsity and overcompleteness in image models

Berkes, P and Turner, RE and Sahani, M (2008) On sparsity and overcompleteness in image models. In: UNSPECIFIED.

Full text not available from this repository.

Abstract

Computational models of visual cortex, and in particular those based on sparse coding, have enjoyed much recent attention. Despite this currency, the question of how sparse or how over-complete a sparse representation should be, has gone without principled answer. Here, we use Bayesian model-selection methods to address these questions for a sparse-coding model based on a Student-t prior. Having validated our methods on toy data, we find that natural images are indeed best modelled by extremely sparse distributions; although for the Student-t prior, the associated optimal basis size is only modestly over-complete.

Item Type: Conference or Workshop Item (UNSPECIFIED)
Subjects: UNSPECIFIED
Divisions: Div F > Computational and Biological Learning
Depositing User: Cron Job
Date Deposited: 07 Mar 2014 12:20
Last Modified: 10 Mar 2014 18:05
DOI:

Actions (login required)

View Item