Over the last decade, fully distributed models have become dominant in conn
ectionist psychological modelling, whereas the virtues of localist models h
ave been underestimated, This target article illustrates some of the benefi
ts of localist modelling. Localist models are characterized by the presence
of localist representations rather than the absence of distributed represe
ntations. A generalized localist model is proposed that exhibits many of di
e properties of fully distributed models. It can be applied to a number of
problems that are difficult for fully distributed models, and its applicabi
lity can be extended through comparisons with a number of classic mathemati
cal models of behaviour. There are reasons why localist models have been un
derused, though these often misconstrue die localist position. In particula
r, many conclusions about connectionist representation, based on neuroscien
tific observation, can be called into question. There are still some proble
ms inherent in the application of fully distributed systems and some inadeq
uacies in proposed solutions to these problems. In the domain of psychologi
cal modelling, localist modelling is to be preferred.