A robust algorithm in sequentially selecting subset time series systems using neural networks

Jack H W Penm, T. J. Brailsford, R. D. Terrell

Research output: Contribution to journalArticleResearchpeer-review

6 Citations (Scopus)

Abstract

In this paper a numerically robust lattice-ladder learning algorithm is presented that sequentially selects the best specification of a subset time series system using neural networks. We have been able to extend the relevance of multilayered neural networks and so more effectively model a greater array of time series situations. We have recognized that many connections between nodes in layers are unnecessary and can be deleted. So we have introduced inhibitor arcs, reflecting inhibitive synapses. We also allow for connections between nodes in layers which have variable strengths at different points of time by introducing additionally excitatory arcs, reflecting excitatory synapses. The resolving of both time and order updating leads to optimal synaptic weight updating and allows for optimal dynamic node creation/deletion within the extended neural network. The paper presents two applications that demonstrate the usefulness of the process.

Original languageEnglish
Pages (from-to)389-412
Number of pages24
JournalJournal of Time Series Analysis
Volume21
Issue number4
DOIs
Publication statusPublished - 2000
Externally publishedYes

Fingerprint

Series System
Robust Algorithm
Set theory
Time series
Synapse
Neural Networks
Neural networks
Subset
Updating
Arc of a curve
Vertex of a graph
Ladders
Learning algorithms
Deletion
Inhibitor
Learning Algorithm
Specification
Specifications
Demonstrate
Node

Cite this

Penm, Jack H W ; Brailsford, T. J. ; Terrell, R. D. / A robust algorithm in sequentially selecting subset time series systems using neural networks. In: Journal of Time Series Analysis. 2000 ; Vol. 21, No. 4. pp. 389-412.
@article{db6637b966ba4d9896209fe5200cefbf,
title = "A robust algorithm in sequentially selecting subset time series systems using neural networks",
abstract = "In this paper a numerically robust lattice-ladder learning algorithm is presented that sequentially selects the best specification of a subset time series system using neural networks. We have been able to extend the relevance of multilayered neural networks and so more effectively model a greater array of time series situations. We have recognized that many connections between nodes in layers are unnecessary and can be deleted. So we have introduced inhibitor arcs, reflecting inhibitive synapses. We also allow for connections between nodes in layers which have variable strengths at different points of time by introducing additionally excitatory arcs, reflecting excitatory synapses. The resolving of both time and order updating leads to optimal synaptic weight updating and allows for optimal dynamic node creation/deletion within the extended neural network. The paper presents two applications that demonstrate the usefulness of the process.",
author = "Penm, {Jack H W} and Brailsford, {T. J.} and Terrell, {R. D.}",
year = "2000",
doi = "10.1111/1467-9892.00190",
language = "English",
volume = "21",
pages = "389--412",
journal = "Journal of Time Series Analysis",
issn = "0143-9782",
publisher = "Wiley-Blackwell",
number = "4",

}

A robust algorithm in sequentially selecting subset time series systems using neural networks. / Penm, Jack H W; Brailsford, T. J.; Terrell, R. D.

In: Journal of Time Series Analysis, Vol. 21, No. 4, 2000, p. 389-412.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - A robust algorithm in sequentially selecting subset time series systems using neural networks

AU - Penm, Jack H W

AU - Brailsford, T. J.

AU - Terrell, R. D.

PY - 2000

Y1 - 2000

N2 - In this paper a numerically robust lattice-ladder learning algorithm is presented that sequentially selects the best specification of a subset time series system using neural networks. We have been able to extend the relevance of multilayered neural networks and so more effectively model a greater array of time series situations. We have recognized that many connections between nodes in layers are unnecessary and can be deleted. So we have introduced inhibitor arcs, reflecting inhibitive synapses. We also allow for connections between nodes in layers which have variable strengths at different points of time by introducing additionally excitatory arcs, reflecting excitatory synapses. The resolving of both time and order updating leads to optimal synaptic weight updating and allows for optimal dynamic node creation/deletion within the extended neural network. The paper presents two applications that demonstrate the usefulness of the process.

AB - In this paper a numerically robust lattice-ladder learning algorithm is presented that sequentially selects the best specification of a subset time series system using neural networks. We have been able to extend the relevance of multilayered neural networks and so more effectively model a greater array of time series situations. We have recognized that many connections between nodes in layers are unnecessary and can be deleted. So we have introduced inhibitor arcs, reflecting inhibitive synapses. We also allow for connections between nodes in layers which have variable strengths at different points of time by introducing additionally excitatory arcs, reflecting excitatory synapses. The resolving of both time and order updating leads to optimal synaptic weight updating and allows for optimal dynamic node creation/deletion within the extended neural network. The paper presents two applications that demonstrate the usefulness of the process.

UR - http://www.scopus.com/inward/record.url?scp=0040364154&partnerID=8YFLogxK

U2 - 10.1111/1467-9892.00190

DO - 10.1111/1467-9892.00190

M3 - Article

VL - 21

SP - 389

EP - 412

JO - Journal of Time Series Analysis

JF - Journal of Time Series Analysis

SN - 0143-9782

IS - 4

ER -