Joint Spatial and Temporal Structure Learning for Task based Control

Authors:
Kingsley Sage;Hilary Buxton
Affiliations:
University of Sussex, UK;University of Sussex, UK
Venue:
ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 2 - Volume 02
Year:
2004

Citing 0
Cited 3

Learning temporal structure for task based control

Image and Vision Computing
How close are we to solving the problem of automated visual surveillance?: A review of real-world surveillance, scientific progress and evaluative mechanisms

Machine Vision and Applications
Learning Object Representations Using Sequential Patterns

AI '08 Proceedings of the 21st Australasian Joint Conference on Artificial Intelligence: Advances in Artificial Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present an example of a joint spatial and temporal task learning algorithm that results in a generative model that has applications for on-line visual control. We review work on learning transformed mixture of gaussians (due to Frey and Jojic) and Variable Length Markov Models (VLMMS due to Ron, Singer and Tishby). We show how a temporal model, learned through an extension of VLMMs to deal with multinomially distributed input symbol vectors, can be used as an improvement on Maximum Likelihood (ML) for prior parameter estimation for the Expectation Maximisation (EM) process.