| | |
Summary: LETTER Communicated by Sebastian Seung
Supervised Learning Through Neuronal Response
Modulation
Christian D. Swinehart
cds@brandeis. edu.
L.F. Abbott
abbott@brandeis. edu.
Volen Center and Department of Biology, Brandeis University,
Waltham, MA 02454, U.S.A.
Neural networks that are trained to perform specific tasks must be de-
veloped through a supervised learning procedure. This normally takes
the form of direct supervision of synaptic plasticity. We explore the idea
that supervision takes place instead through the modulation of neuronal
excitability. Such supervision can be done using conventional synaptic
feedback pathways rather than requiring the hypothetical actions of un-
known modulatory agents. During task learning, supervised response
modulation guides Hebbian synaptic plasticity indirectly by establish-
ing appropriate patterns of correlated network activity. This results in ro-
bust learning of function approximation tasks even when multiple output
units representing different functions share large amounts of common in-
|
