Learning regular grammars on connection architectures

The authors present results on learning regular grammars as well as developing extensions to learning multidimensional random fields. In learning a regular grammar, they use recent results on the stochastic representation of strongly connected regular grammars in order to derive an algorithm based on mutual information for learning the minimal state set as well as the production rules of the grammar. These learning results are then extended to multiple dimensions by extending the state structure of the regular grammar to the neighborhood structure of multidimensional random fields. This allows the authors to learn textures for image segmentation and reconstruction. The implementation of the learning algorithms on connection architectures is described.