Free lunches for neural network search.

In this paper we prove that for a variety of practical situations, the no-free-lunch (NFL) theorem does not apply to algorithms that search the space of artificial neural networks, such as evolutionary algorithms. We find, in particular, that, while conditions under which NFL applies exist, these require extremely restrictive symmetries on the set of possible problems which are unlikely encountered in practice. In other words, not all algorithms are equally good at finding neural networks that solve problems under all possible performance measures: a superior search algorithm for this domain does exist.