Implementing an Intelligent Moving Average with a Neural Network

Nuno Miguel Cavalheiro Marques

doi:10.3233/978-1-60750-606-5-1129

Implementing an Intelligent Moving Average with a Neural Network

Nuno Miguel Cavalheiro Marques

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Citation (Scopus)

Abstract

Recent results in hybrid neural networks using extended versions of the core method have shown that we can use background knowledge to guide back-propagation learning. This paper further explores this ideas by adding numeric functions to the encoded knowledge and using the traditional recursive Elman neural network model. An illustration of the properties of these neural networks will be used to calculate a simple moving average. Simulations on generated data and on the Eurostoxx50 financial index will illustrate the potential of such a strategy.

Original language	Unknown
Title of host publication	ECAI
Editors	H Coelho, R Studer, M Wooldridge
Publisher	IOS Press
Pages	1129-1130
DOIs	https://doi.org/10.3233/978-1-60750-606-5-1129
Publication status	Published - 1 Jan 2010
Event	European Conference on Artificial Intelligence (ECAI) - Duration: 1 Jan 2010 → …

Conference

Conference	European Conference on Artificial Intelligence (ECAI)
Period	1/01/10 → …

Access to Document

10.3233/978-1-60750-606-5-1129

Cite this

@inproceedings{ee5ba68273ab4a28b67df4837757d418,

title = "Implementing an Intelligent Moving Average with a Neural Network",

abstract = "Recent results in hybrid neural networks using extended versions of the core method have shown that we can use background knowledge to guide back-propagation learning. This paper further explores this ideas by adding numeric functions to the encoded knowledge and using the traditional recursive Elman neural network model. An illustration of the properties of these neural networks will be used to calculate a simple moving average. Simulations on generated data and on the Eurostoxx50 financial index will illustrate the potential of such a strategy.",

author = "{Cavalheiro Marques}, {Nuno Miguel}",

year = "2010",

month = jan,

day = "1",

doi = "10.3233/978-1-60750-606-5-1129",

language = "Unknown",

pages = "1129--1130",

editor = "H Coelho and R Studer and M Wooldridge",

booktitle = "ECAI",

publisher = "IOS Press",

address = "Netherlands",

note = "European Conference on Artificial Intelligence (ECAI) ; Conference date: 01-01-2010",

}

TY - GEN

T1 - Implementing an Intelligent Moving Average with a Neural Network

AU - Cavalheiro Marques, Nuno Miguel

PY - 2010/1/1

Y1 - 2010/1/1

N2 - Recent results in hybrid neural networks using extended versions of the core method have shown that we can use background knowledge to guide back-propagation learning. This paper further explores this ideas by adding numeric functions to the encoded knowledge and using the traditional recursive Elman neural network model. An illustration of the properties of these neural networks will be used to calculate a simple moving average. Simulations on generated data and on the Eurostoxx50 financial index will illustrate the potential of such a strategy.

AB - Recent results in hybrid neural networks using extended versions of the core method have shown that we can use background knowledge to guide back-propagation learning. This paper further explores this ideas by adding numeric functions to the encoded knowledge and using the traditional recursive Elman neural network model. An illustration of the properties of these neural networks will be used to calculate a simple moving average. Simulations on generated data and on the Eurostoxx50 financial index will illustrate the potential of such a strategy.

U2 - 10.3233/978-1-60750-606-5-1129

DO - 10.3233/978-1-60750-606-5-1129

M3 - Conference contribution

SP - 1129

EP - 1130

BT - ECAI

A2 - Coelho, H

A2 - Studer, R

A2 - Wooldridge, M

PB - IOS Press

T2 - European Conference on Artificial Intelligence (ECAI)

Y2 - 1 January 2010

ER -