Open Peer Commentary Clark & Thornton: Trading spaces
Constraining solution space to improve generalization
John A. Bullinaria a1 a1 Centre for Speech and Language, Department of Psychology, Birkbeck College, London WC1E 7HX, United Kingdom
johnbull@ed.ac.uk
Abstract
I suggest that the difficulties inherent in discovering the
hidden regularities in realistic (type-2) problems can often be
resolved by learning algorithms employing simple constraints (such as
symmetry and the importance of local information) that are natural
from an evolutionary point of view. Neither “heavy-duty
nativism” nor “representational recoding” appear
to offer totally appropriate descriptions of such natural learning
processes.
