We report research on the assessment of Boolean minimization in symbol
ic empirical learning. We view training examples as logical expression
s and implement Boolean Minimization (BM) heuristics to optimize input
and to learn symbolic knowledge rules. We base our work on a BM learn
ing system called BML. BML includes three components: a preprocessing,
a BM, and a postprocessing component. The system incorporates Espress
o-II, a popular system in very large scale integration design. The pre
processing and postprocessing components include utilities that suppor
t preparation of training examples.