Learning regular grammars on connection architectures
Smith, K.R.; Miller, M.I.
Acoustics, Speech, and Signal Processing, 1989. ICASSP-89., 1989 International Conference on
Volume , Issue , 23-26 May 1989 Page(s):2501 - 2504 vol.4
Digital Object Identifier 10.1109/ICASSP.1989.266975
Summary: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
View citation and abstract |
Cart
