In:
Behavioral and Brain Sciences, Cambridge University Press (CUP), Vol. 23, No. 4 ( 2000-08), p. 467-468
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.
Type of Medium:
Online Resource
ISSN:
0140-525X
,
1469-1825
DOI:
10.1017/S0140525X00223352
Language:
English
Publisher:
Cambridge University Press (CUP)
Publication Date:
2000
detail.hit.zdb_id:
1481789-5
detail.hit.zdb_id:
423721-3
SSG:
7,11
Bookmarklink