Title :
Using feedforward networks to distinguish multivariate populations
Author :
Stinchcombe, Maxwell ; White, Halbert
Author_Institution :
California Univ., San Diego, La Jolla, CA, USA
Abstract :
It is shown how feedforward neural networks can be used to construct convenient and informative tests for nonspecific differences between populations with multivariate attributes. The key to the power of these tests is of independent interest: under mild conditions, feedforward neural networks have the universal approximation property when parameterized by weights in arbitrarily small neighborhoods
Keywords :
feedforward neural nets; feedforward networks; multivariate populations; neural networks; universal approximation property; Computer networks; Data analysis; Feedforward neural networks; Neural networks; Performance evaluation; Pharmaceuticals; Power generation economics; Stochastic processes; Testing; Training data;
Conference_Titel :
Neural Networks, 1992. IJCNN., International Joint Conference on
Conference_Location :
Baltimore, MD
Print_ISBN :
0-7803-0559-0
DOI :
10.1109/IJCNN.1992.287091
