✦ LIBER ✦

A neural network for identification of economic indicators using an answer-in-weights scheme

✍ Scribed by Takehiko Ogawa; Yukio Kosugi

Publisher: John Wiley and Sons
Year: 1998
Tongue: English
Weight: 212 KB
Volume: 29
Category: Article
ISSN: 0882-1666
DOI: 10.1002/(sici)1520-684x(199805)29:5<29::aid-scj4>3.0.co;2-p

No coin nor oath required. For personal study only.

✦ Synopsis

In the prediction of future economic indicators, periodic and long-term components are often separately handled in a pre-divided form. We propose a network model that can identify the two parts simultaneously. To improve the generalization ability beyond that offered by conventional multilayer networks in prediction problems, this network uses a parametric structure utilizing a priori information on the problem. The model consists of two network components arranged in an answer-in-weights structure, which requires a solution to appear in the weights and expresses the fluctuation of economic indicators by multiplying the outputs. Simulations on two examples of economic data were done to confirm the model validity. ©1998

📜 SIMILAR VOLUMES

A framework development for predicting t

A framework development for predicting the longitudinal dispersion coefficient in natural streams using an artificial neural network

✍ R. Noori; A.R. Karbassi; H. Mehdizadeh; M. Vesali-Naseh; M.S. Sabahi 📂 Article 📅 2010 🏛 American Institute of Chemical Engineers 🌐 English ⚖ 432 KB

## Abstract The main objective of the present investigation is to predict longitudinal dispersion coefficient (__K__~x~) in natural streams using artificial neural network (ANN) technique based on most famous training functions such as Trainlm, Trainrp, Trainscg, Trainoss, and so on. To achieve the