On the Nonlearnability of a Single Spiking Neuron
We study the computational complexity of training a single spiking neuron with binary coded inputs and output that, in addition to adaptive weights and a threshold, has adjustable synaptic delays. A synchronization technique is introduced so that the results concerning the nonlearn-ability of spikin...
Saved in:
Published in | Neural computation Vol. 17; no. 12; pp. 2635 - 2647 |
---|---|
Main Authors | , |
Format | Journal Article |
Language | English |
Published |
One Rogers Street, Cambridge, MA 02142-1209, USA
MIT Press
01.12.2005
MIT Press Journals, The |
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | We study the computational complexity of training a single spiking neuron
with binary coded inputs and output that, in addition to adaptive weights and a threshold, has adjustable synaptic delays. A synchronization technique is introduced so that the results concerning the nonlearn-ability of spiking neurons with binary delays are generalized to arbitrary real-valued delays. In particular, the consistency problem for
with programmable weights, a threshold, and delays, and its approximation version are proven to be
-complete. It follows that the spiking neurons with arbitrary synaptic delays are not properly PAC learnable and do not allow robust learning unless
=
. In addition, the representation problem for
, a question whether an
-variable Boolean function given in DNF (or as a disjunction of
(
) threshold gates) can be computed by a spiking neuron, is shown to be
-hard. |
---|---|
Bibliography: | December, 2005 ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
ISSN: | 0899-7667 1530-888X |
DOI: | 10.1162/089976605774320601 |