DocumentCode
3456751
Title
A multinomial characterization of feedforward neural networks
Author
Lehmann, Bruce N.
Author_Institution
Graduate Sch. of Int. Relations & Pacific Studies, California Univ., San Diego, La Jolla, CA, USA
fYear
1995
fDate
9-11 Apr 1995
Firstpage
79
Lastpage
86
Abstract
The purpose of the paper is to examine neural networks in terms of a particular probability model: a multinomial distribution characterization of the conditional mean. This characterization suggests circumstances in which networks need only provide good local approximations and a new parsimonious neural network model. The paper provides an empirical application to interest rate volatility
Keywords
economics; feedforward neural nets; forecasting theory; multilayer perceptrons; probability; conditional mean; empirical application; feedforward neural networks; interest rate volatility; local approximations; multinomial distribution characterization; parsimonious neural network model; probability model; Convergence; Feedforward neural networks; International relations; Kernel; Neural networks; Permission; Probability; Random variables; Reactive power; Statistics;
fLanguage
English
Publisher
ieee
Conference_Titel
Computational Intelligence for Financial Engineering, 1995.,Proceedings of the IEEE/IAFE 1995
Conference_Location
New York, NY
Print_ISBN
0-7803-2145-6
Type
conf
DOI
10.1109/CIFER.1995.495255
Filename
495255
Link To Document