|
NeuroCOLT
Technical Report NC-TR-97-002
Size
of multilayer networks for exact learning:
analytic approach
A.
Elisseeff and H. Paugam-Moisy
ENS Lyon
France
Abstract
This article presents a new result about the size of a multilayer
neural network computing real outputs for exact learning of a finite
set of real samples. The architecture of the network is feedforward,
with one hidden layer and several outputs. Starting from a fixed training
set, we consider the network as a function of its weights. We derive,
for a wide family of transfer functions, a lower and an upper bound
on the number of hidden units for exact learning, given the size of
the dataset and the dimensions of the input and output spaces.
Download Compressed Postscript
|