Journal of the ACM (JACM)
An introduction to computational learning theory
An introduction to computational learning theory
Boolean Formulas are Hard to Learn for most Gate Bases
ALT '99 Proceedings of the 10th International Conference on Algorithmic Learning Theory
STOC '84 Proceedings of the sixteenth annual ACM symposium on Theory of computing
Hi-index | 0.00 |
This paper presents a memoryless categorization learner that predicts differences in category complexity found in several psycholinguistic and psychological experiments. In particular, this learner predicts the order of difficulty of learning simple Boolean categories, including the advantage of conjunctive categories over the disjunctive ones (an advantage that is not typically modeled by the statistical approaches). It also models the effect of labeling (positive and negative labels vs. positive labels of two different kinds) on category complexity. This effect has implications for the differences between learning a single category (e.g., a phonological class of segments) vs. a set of non-overlapping categories (e.g., affixes in a morphological paradigm).