An Internal Teacher for Neural Computation

Contextual signals might supervise discovery of coherently varying information between cortical modules computing different functions of their receptive field input. This hypothesis is explored in two sets of computational experiments, one studying the effects on learning of long-range unidirectional contextual signals mediated by intervening processors, and the other showing contextually supervised discovery of a high-order variable in a multi-layer network.


Published in:
Behavioral and Brain Sciences, 20, 4, 687- 688
Year:
1997
Note:
Long commentary with new experiments for the target article by Phillips, W. A. and Singer, W. (1997) In search of common foundations for cortical computation. Behavioral and Brain Sciences, 20(4)
Laboratories:




 Record created 2006-01-12, last modified 2018-03-17

n/a:
Download fulltext
PDF

Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)