An information theoretic ART for robust unsupervised learning

In this paper, an information-theoretic-based adaptive resonance theory (IT-ART) neural network architecture is presented. Each IT-ART category is defined by the first and second order statistics (mean and covariance matrix) of the cluster or class it represents. This information is used to estimate...

Full description

Saved in:
Bibliographic Details
Main Authors: da Silva, Leonardo Enzo Brito, Wunsch, Donald C.
Format: Conference Proceeding
Language:English
Subjects:
Computer architecture
Covariance matrices
Euclidean distance
Kernel
Neural networks
Subspace constraints
Unsupervised learning
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, an information-theoretic-based adaptive resonance theory (IT-ART) neural network architecture is presented. Each IT-ART category is defined by the first and second order statistics (mean and covariance matrix) of the cluster or class it represents. This information is used to estimate probability density functions (multivariate Gaussians) and compute the activation functions. The match function of the vigilance check is based on Renyi's quadratic cross-entropy: it is the cross information potential. Experiments involving several real world and synthetic data sets were carried out to assess the performance of IT-ART, which was measured in terms of external validity indices. IT-ART expanded the range of successful vigilance parameter values in these tests.
ISSN:2161-4407
DOI:10.1109/IJCNN.2016.7727583