Unsupervised learning in second-order neural networks for motion analysis

Maul, Tomas and Baba, Mohd Sapiyan (2011) Unsupervised learning in second-order neural networks for motion analysis. Neurocomputing, 74 (6). pp. 884-895. ISSN 0925-2312, DOI https://doi.org/10.1016/j.neucom.2010.09.023.

Full text not available from this repository.
Official URL: https://doi.org/10.1016/j.neucom.2010.09.023


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.

Item Type: Article
Uncontrolled Keywords: Second-order neural networks; Motion analysis; Unsupervised learning; Dendritic computation; Feature correspondences
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
T Technology > T Technology (General)
Divisions: Faculty of Computer Science & Information Technology > Department of Artificial Intelligence
Depositing User: Ms Maisarah Mohd Muksin
Date Deposited: 04 Jan 2013 16:23
Last Modified: 15 Nov 2019 03:44
URI: http://eprints.um.edu.my/id/eprint/5670

Actions (login required)

View Item View Item