Computer Science – Neural and Evolutionary Computing
Scientific paper
2004-10-10
Computer Science
Neural and Evolutionary Computing
35 pages, 20 figures
Scientific paper
Using the maximum entropy method, we derive the "adaptive cluster expansion" (ACE), which can be trained to estimate probability density functions in high dimensional spaces. The main advantage of ACE over other Bayesian networks is its ability to capture high order statistics after short training times, which it achieves by making use of a hierarchical vector quantisation of the input data. We derive a scheme for representing the state of an ACE network as a "probability image", which allows us to identify statistically anomalous regions in an otherwise statistically homogeneous image, for instance. Finally, we present some probability images that we obtained after training ACE on some Brodatz texture images - these demonstrate the ability of ACE to detect subtle textural anomalies.
No associations
LandOfFree
Adaptive Cluster Expansion (ACE): A Hierarchical Bayesian Network does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Adaptive Cluster Expansion (ACE): A Hierarchical Bayesian Network, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Adaptive Cluster Expansion (ACE): A Hierarchical Bayesian Network will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-358548