Title :
An estimation framework in a forward-propagation learning rule
Author :
Ohama, Y. ; Fukumura, N. ; Uno, Y.
Author_Institution :
Toyohashi Univ. of Technol., Japan
Abstract :
A forward-propagation learning rule has been proposed to acquire neural inverse models. This rule can solve a credit assignment problem based on Newton-like method. In the current work, we discuss how to estimate the parameters of a multi-layered neural network based on the credit assignment. The suitability of the proposed estimation framework is confirmed by computer simulation.
Keywords :
Newton method; feedforward neural nets; inverse problems; learning (artificial intelligence); multilayer perceptrons; parameter estimation; Newton-like method; computer simulation; credit assignment problem; forward-propagation learning rule; inverse model; multilayered neural network; parameter estimation;
Conference_Titel :
SICE 2004 Annual Conference
Conference_Location :
Sapporo
Print_ISBN :
4-907764-22-7
