Constraint breeding during on-line incremental learning

摘要

An evolutionary algorithm for simultaneously inducing and weighting phonological constraints (Winnow-MaxEnt-Subtree Breeder) is described, analyzed, and illustrated. Implementing weights as sub-population sizes, reproduction with selection executes a new variant of Winnow (Littlestone, 1988), which is shown to converge. A flexible constraint schema, based on the same prosodic and au-tosegmental trees used in representations, is described, together with algorithms for mutation and recombination (mating). The algorithm is applied to explaining abrupt learning curves, and predicts an empirical connection between abruptness and language-particularity.