Neural networks combining local excitatory feedback with recurrent inhibiti
on are valuable models of neocortical processing. However, incorporating th
e attentional modulation observed in cortical neurons is problematic. We pr
opose a simple architecture for attentional processing. Our network consist
s of two reciprocally connected populations of excitatory neurons; a large
population (the map) processes a feedforward sensory input, and a small pop
ulation (the pointer) modulates location and intensity of this processing i
n an attentional manner dependent on a control input to the pointer. This p
ointer-map network has rich dynamics despite its simple architecture and ex
plains general computational features related to attention/intention observ
ed in neocortex, making it interesting both theoretically and experimentall
y.