TY - JOUR
T1 - Approximating functions by neural networks
T2 - A constructive solution in the uniform norm
AU - Meltser, Mark
AU - Shoham, Moshe
AU - Manevitz, Larry M.
PY - 1996/8
Y1 - 1996/8
N2 - A method for constructively approximating functions in the uniform (i.e., maximal error) norm by successive changes in the weights and number of neurons in a neural network is developed. This is a realization of the approximation results of Cybenko, Hecht-Nielsen, Hornik, Stinchcombe, White, Callant, Funahashi, Leshno et al., and others. The constructive approximation in the uniform norm is more appropriate for a number of examples, such as robotic arm motion, and stands in contrast with more standard methods, such as back-propagation, which approximate only in the average error norm.
AB - A method for constructively approximating functions in the uniform (i.e., maximal error) norm by successive changes in the weights and number of neurons in a neural network is developed. This is a realization of the approximation results of Cybenko, Hecht-Nielsen, Hornik, Stinchcombe, White, Callant, Funahashi, Leshno et al., and others. The constructive approximation in the uniform norm is more appropriate for a number of examples, such as robotic arm motion, and stands in contrast with more standard methods, such as back-propagation, which approximate only in the average error norm.
KW - approximating functions
KW - artificial neural networks
KW - constructive approximation
KW - dynamic neural network architecture
KW - feed-forward
KW - uniform norm
UR - http://www.scopus.com/inward/record.url?scp=0030220517&partnerID=8YFLogxK
U2 - 10.1016/0893-6080(95)00124-7
DO - 10.1016/0893-6080(95)00124-7
M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???
AN - SCOPUS:0030220517
SN - 0893-6080
VL - 9
SP - 965
EP - 978
JO - Neural Networks
JF - Neural Networks
IS - 6
ER -