If neuronal models are successful, they will account for specifically
human complex behaviours. Most of these behaviours can be described as
governed by rules. In recent years, much effort has been spent to elu
cidate the neuronal basis of rules, and many researchers have focussed
on modelling rules and regularities underlying language, particularly
those relevant for past-tense formation. After introducing problems p
osed by Fast-tense formation, important aspects of recent controversie
s between connectionists and linguists concerning the nature of rules
will be reviewed and analysed on the basis of elementary simulations.
It is argued that modular networks with varying connection probabiliti
es between their layers would be ideal for modelling learning and proc
essing of past-tense formation, The motivation for postulating such ne
tworks comes from neurobiological models of language and from neuroana
tomical data about cortico-cortical connectivity. Furthermore, such mo
dular networks may explain double dissociations of regular and irregul
ar past-tense formation in neurological patients, as reported in recen
t neuropsychological publications. It is concluded that past-tense for
mation does not pose problems to pattern associators, given that some
structure is built into the network which approximates wirings in the
human cortex.