We argue that existing learning algorithms are often poorly equipped to solve problems involving a certain type of important and widespread regularity that we call 'type-2 regularity'. The solution in these cases is to trade achieved representation against computational search. We investigate several ways in which such a trade-off may be pusued includig simple incremental learning, modular connectionism, and the developmental hypothesis of 'representational redescription'.
|Number of pages||8|
|Journal||Behavioral and Brain Sciences|
|Publication status||Published - 1997|