Learning Adaptive Correlations of Independent Components for Complex Cell Modeling

Motivated in part by the hierarchical processing of the cortex, we build an unsupervised network learning the properties of complex cells in V1. Unlike traditional methods, we model the binary relation among these complex cells, which makes our network less constrained and more adaptive for the conn...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhe Wang, Siwei Luo, Yaping Huang
Format: Conference Proceeding
Language:English
Subjects:
adaptive correlation
Artificial intelligence
Band pass filters
binary relation
Brain modeling
complex cells
Computer networks
Gabor filters
Independent component analysis
Information technology
Instruction sets
Neurons
Nonlinear filters
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Motivated in part by the hierarchical processing of the cortex, we build an unsupervised network learning the properties of complex cells in V1. Unlike traditional methods, we model the binary relation among these complex cells, which makes our network less constrained and more adaptive for the connectivity among these cells. The obtained filters not only emerge properties similar to those of complex cells, but show more local structures than traditional method such as TICA.
DOI:10.1109/AICI.2009.281