Evolvability from learning algorithms
Vitaly Feldman · 2008
Valiant has recently introduced a framework for analyzing the capabilities and the limitations of the evolutionary process of random change guided by selection. In his framework the process of acquiring a complex functionality is viewed as a substantially restricted form of PAC learning of an unknown function from a certain set of functions. Valiant showed that classes of functions evolvable in his model are also learnable in the statistical query (SQ) model of Kearns and asked whether the converse is true.