Paper Info
Title
Phase synchrony facilitates binding and segmentation of natural images in a coupled neural oscillator network.
Abstract
Synchronization has been suggested as a mechanism of binding distributed feature representations facilitating segmentation of visual stimuli. Here we investigate this concept based on unsupervised learning using natural visual stimuli. We simulate dual-variable neural oscillators with separate activation and phase variables. The binding of a set of neurons is coded by synchronized phase variables. The network of tangential synchronizing connections learned from the induced activations exhibits small-world properties and allows binding even over larger distances. We evaluate the resulting dynamic phase maps using segmentation masks labeled by human experts. Our simulation results show a continuously increasing phase synchrony between neurons within the labeled segmentation masks. The evaluation of the network dynamics shows that the synchrony between network nodes establishes a relational coding of the natural image inputs. This demonstrates that the concept of binding by synchrony is applicable in the context of unsupervised learning using natural visual stimuli.
Year
DOI
Venue
2014
10.3389/fncom.2013.00195
FRONTIERS IN COMPUTATIONAL NEUROSCIENCE
Keywords
Field
DocType
oscillation,binding,synchronization,normative model,unsupervised learning,scene segmentation,object label,natural image statistics
Synchronization,Network dynamics,Computer science,Segmentation,Synchronizing,Node (networking),Coding (social sciences),Unsupervised learning,Artificial intelligence,Machine learning,Visual perception
Journal
Volume
ISSN
Citations 
7
1662-5188
5
PageRank 
References 
Authors
0.49
19
2
Name
Order
Citations
PageRank
Holger Finger1222.43
Peter König218176.48