Function estimation by feedforward sigmoidal networks with bounded weights

Function estimation by feedforward sigmoidal networks with bounded weights [electronic resource]

The authors address the problem of PAC (probably and approximately correct) learning functions f : [0, 1]{sup d} {r_arrow} [-K, K] based on iid (independently and identically distributed) sample generated according to an unknown distribution, by using feedforward sigmoidal networks. They use two bas...

Full description

Saved in:
Bibliographic Details
Online Access: Online Access
Corporate Author: Oak Ridge National Laboratory. (Researcher)
Format: Government Document Electronic eBook
Language:English
Published: Washington, D.C. : Oak Ridge, Tenn. : United States. Dept. of Energy ; distributed by the Office of Scientific and Technical Information, U.S. Dept. of Energy, 1996.
Subjects:
Functions.
Neural Networks.
Probabilistic Estimation.
Learning.
Performance.
Mathematics, Computers, Information Science, Management, Law, Miscellaneous.

Internet

Online Access

Online

Holdings details from Online
Call Number: E 1.99:CONF-9606113--2
E 1.99:CONF-9606113--2 Available

Similar Items