Sciweavers

NIPS
2001

Learning Lateral Interactions for Feature Binding and Sensory Segmentation

13 years 5 months ago
Learning Lateral Interactions for Feature Binding and Sensory Segmentation
We present a new approach to the supervised learning of lateral interactions for the competitive layer model (CLM) dynamic feature binding architecture. The method is based on consistency conditions, which were recently shown to characterize the attractor states of this linear threshold recurrent network. For a given set of training examples the learning problem is formulated as a convex quadratic optimization problem in the lateral interaction weights. An efficient dimension reduction of the learning problem can be achieved by using a linear superposition of basis interactions. We show the successful application of the method to a medical image segmentation problem of fluorescence microscope cell images.
Heiko Wersing
Added 31 Oct 2010
Updated 31 Oct 2010
Type Conference
Year 2001
Where NIPS
Authors Heiko Wersing
Comments (0)