Localist representation can improve efficiency for detection and counting
Horace Barlow a1andAnthony Gardner-Medwin a2 a1 Physiological Laboratory, Cambridge CB2 3EG, England
hbb10@cam.ac.uk a2 Department of Physiology, University College London, London WC1E 6BT, England
a.gardner-medwin@ucl.ac.uk
Abstract
Almost all representations have both distributed and localist aspects, depending upon what properties of the data are being considered. With noisy data, features represented in a localist way can be detected very efficiently, and in binary representations they can be counted more efficiently than those represented in a distributed way. Brains operate in noisy environments, so the localist representation of behaviourally important events is advantageous, and fits what has been found experimentally. Distributed representations require more neurons to perform as efficiently, but they do have greater versatility.
