THE UNIQUENESS THEOREM FOR COMPLEX-VALUED NEURAL NETWORKS WITH THRESHOLD PARAMETERS AND THE REDUNDANCY OF THE PARAMETERS
2008 ◽
Vol 18
(02)
◽
pp. 123-134
◽
Keyword(s):
This paper will prove the uniqueness theorem for 3-layered complex-valued neural networks where the threshold parameters of the hidden neurons can take non-zeros. That is, if a 3-layered complex-valued neural network is irreducible, the 3-layered complex-valued neural network that approximates a given complex-valued function is uniquely determined up to a finite group on the transformations of the learnable parameters of the complex-valued neural network.
2009 ◽
Vol 19
(02)
◽
pp. 137-137
◽
Keyword(s):
2012 ◽
Vol 3
(2)
◽
pp. 81-116
2009 ◽
Vol 72
(10-12)
◽
pp. 2227-2234
◽
Keyword(s):
2001 ◽
Vol 11
(01)
◽
pp. 33-42
◽