Unsupervised learning in second-order neural networks for motion analysis

Authors:
Toma Maul;Sapiyan Baba
Affiliations:
School of Computer Science, The University of Nottingham Malaysia Campus, Malaysia;Faculty of Computer Science & IT, University Malaya, Malaysia
Venue:
Neurocomputing
Year:
2011

Citing 7
Cited 1

A survey of the Hough transform

Computer Vision, Graphics, and Image Processing
Product units: a computationally powerful and biologically plausible extension to backpropagation networks

Neural Computation
A model of the directional selectivity circuit in retina: transformations by neurons singly and in concert

Single neuron computation
Advances in Computational Stereo

IEEE Transactions on Pattern Analysis and Machine Intelligence
Biophysics of Computation: Information Processing in Single Neurons (Computational Neuroscience Series)

Biophysics of Computation: Information Processing in Single Neurons (Computational Neuroscience Series)
A self-organizing map of sigma-pi units

Neurocomputing
Review:

Neural Computation

Early experiments with neural diversity machines

Neurocomputing

Quantified Score

Hi-index	0.01

Visualization

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.