Nonlinear spike-and-slab sparse coding for interpretable image encoding.
Sparse coding is a popular approach to model natural images but has faced two main challenges: modelling low-level image components (such as edge-like structures and their occlusions) and modelling varying pixel intensities. Traditionally, images are modelled as a sparse linear superposition of dict...
Main Authors: | Jacquelyn A Shelton, Abdul-Saboor Sheikh, Jörg Bornschein, Philip Sterne, Jörg Lücke |
---|---|
Format: | Article |
Language: | English |
Published: |
Public Library of Science (PLoS)
2015-01-01
|
Series: | PLoS ONE |
Online Access: | http://europepmc.org/articles/PMC4425358?pdf=render |
Similar Items
-
Are v1 simple cells optimized for visual occlusions? A comparative study.
by: Jörg Bornschein, et al.
Published: (2013-01-01) -
The Design of a Simple, Spiking Sparse Coding Algorithm for Memristive Hardware
by: Woods, Walt
Published: (2016) -
Robust detection of neural spikes using sparse coding based features
by: Zuozhi Liu, et al.
Published: (2020-06-01) -
Bayesian variable selection with spike-and-slab priors
by: Agarwal, Anjali
Published: (2016) -
On efficient sparse spike coding schemes for learning natural scenes in the primary visual cortex
by: Perrinet Laurent
Published: (2007-07-01)