Feature Selection with Exception Handling - An Example from PhonologyGabrieleSchelerauthorThe goal in this paper is to show how the classification of
phonetic features to phonemes can be acquired. This classificational process is modeled by a supervised feature
selection method, based on adaptive distance measures.
Exception handling is incorporated into a learned distance function by pointwise additions of Boolean functions for
individual pattern combinations. An important result is the
differentiation of rules and exceptions during learning.Speech1994SpringerConference Paper