A Constructive, Incremental-Learning Network for Mixture Modeling and Classification
MetadataShow full item record
Gaussian ARTMAP (GAM) is a supervised-learning adaptive resonance theory (ART) network that uses Gaussian-defined receptive fields. Like other ART networks, GAM incrementally learns and constructs a representation of sufficient complexity to solve a problem it is trained on. GAM's representation is a Gaussian mixture model of the input space, with learned mappings from the mixture components to output classes. We show a close relationship between GAM and the well-known Expectation-Maximization (EM) approach to mixture-modeling. GAM outperforms an EM classification algorithm on a classification benchmark, thereby demonstrating the advantage of the ART match criterion for regulating learning, and the ARTMAP match tracking operation for incorporate environmental feedback in supervised learning situations.