Unsupervised learning in second-order neural networks for motion analysis
Document Type
Article
Publication Date
1-1-2011
Abstract
This paper demonstrates how unsupervised learning based on Hebb-like mechanisms is sufficient for training second-order neural networks to perform different types of motion analysis. The paper studies the convergence properties of the network in several conditions, including different levels of noise and motion coherence and different network configurations. We demonstrate the effectiveness of a novel variability dependent learning mechanism, which allows the network to learn under conditions of large feature similarity thresholds, which is crucial for noise robustness. The paper demonstrates the particular relevance of second-order neural networks and therefore correlation based approaches as contributing mechanisms for directional selectivity in the retina.
Keywords
Second-order neural networks, Motion analysis, Unsupervised learning, Dendritic computation, Feature correspondences
Divisions
ai
Publication Title
Neurocomputing
Volume
74
Issue
6
Publisher
Elsevier