Timezone: »

On Sparsity and Overcompleteness in Image Models
Pietro Berkes · Richard Turner · Maneesh Sahani

Wed Dec 05 10:30 AM -- 10:40 AM (PST) @

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 overcomplete.

Author Information

Pietro Berkes (Brandeis University)
Richard Turner (University of Cambridge)
Maneesh Sahani (Gatsby Unit, UCL)

More from the Same Authors