Artificial Neural Networks: Temporal Networks

Y. S. Park; T. S. Chon

doi:10.1016/B978-008045405-4.00163-4

Artificial Neural Networks: Temporal Networks

Y. S. Park, T. S. Chon

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

2 Citations (Scopus)

Abstract

Since the level of disturbance rapidly increases in our environment due to unprecedented population aggregation and industrial development, revealing temporal development in ecological processes is critically important (e.g., long-term evaluation of global warming, changes in community dynamics in pollution, response behaviors to toxic chemicals). Various models used in temporal networks are selected from artificial neural networks, and feasibility in analyzing complex temporal data is discussed through supervised and unsupervised learning processes in this article. In addition, some selected examples are provided to demonstrate application of temporal networks to ecological and behavioral data.

Original language	English
Title of host publication	Encyclopedia of Ecology, Five-Volume Set
Publisher	Elsevier
Pages	245-254
Number of pages	10
Volume	1-5
ISBN (Electronic)	9780080454054
DOIs	https://doi.org/10.1016/B978-008045405-4.00163-4
Publication status	Published - 1 Jan 2008

Bibliographical note

Publisher Copyright:
Published by Elsevier B.V.

Keywords

Artificial neural network
Ecological modeling
Partial recurrent network
Real-time recurrent network
Recurrent neural networks
Temporal neural networks
Time delay neural network

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1016/B978-008045405-4.00163-4

Cite this

@inbook{597b22d76e584de097599d725f958aa3,

title = "Artificial Neural Networks: Temporal Networks",

abstract = "Since the level of disturbance rapidly increases in our environment due to unprecedented population aggregation and industrial development, revealing temporal development in ecological processes is critically important (e.g., long-term evaluation of global warming, changes in community dynamics in pollution, response behaviors to toxic chemicals). Various models used in temporal networks are selected from artificial neural networks, and feasibility in analyzing complex temporal data is discussed through supervised and unsupervised learning processes in this article. In addition, some selected examples are provided to demonstrate application of temporal networks to ecological and behavioral data.",

keywords = "Artificial neural network, Ecological modeling, Partial recurrent network, Real-time recurrent network, Recurrent neural networks, Temporal neural networks, Time delay neural network",

author = "Park, {Y. S.} and Chon, {T. S.}",

note = "Publisher Copyright: Published by Elsevier B.V.",

year = "2008",

month = jan,

day = "1",

doi = "10.1016/B978-008045405-4.00163-4",

language = "English",

volume = "1-5",

pages = "245--254",

booktitle = "Encyclopedia of Ecology, Five-Volume Set",

publisher = "Elsevier",

address = "Netherlands",

}

TY - CHAP

T1 - Artificial Neural Networks

T2 - Temporal Networks

AU - Park, Y. S.

AU - Chon, T. S.

N1 - Publisher Copyright: Published by Elsevier B.V.

PY - 2008/1/1

Y1 - 2008/1/1

N2 - Since the level of disturbance rapidly increases in our environment due to unprecedented population aggregation and industrial development, revealing temporal development in ecological processes is critically important (e.g., long-term evaluation of global warming, changes in community dynamics in pollution, response behaviors to toxic chemicals). Various models used in temporal networks are selected from artificial neural networks, and feasibility in analyzing complex temporal data is discussed through supervised and unsupervised learning processes in this article. In addition, some selected examples are provided to demonstrate application of temporal networks to ecological and behavioral data.

AB - Since the level of disturbance rapidly increases in our environment due to unprecedented population aggregation and industrial development, revealing temporal development in ecological processes is critically important (e.g., long-term evaluation of global warming, changes in community dynamics in pollution, response behaviors to toxic chemicals). Various models used in temporal networks are selected from artificial neural networks, and feasibility in analyzing complex temporal data is discussed through supervised and unsupervised learning processes in this article. In addition, some selected examples are provided to demonstrate application of temporal networks to ecological and behavioral data.

KW - Artificial neural network

KW - Ecological modeling

KW - Partial recurrent network

KW - Real-time recurrent network

KW - Recurrent neural networks

KW - Temporal neural networks

KW - Time delay neural network

UR - http://www.scopus.com/inward/record.url?scp=85069568855&partnerID=8YFLogxK

U2 - 10.1016/B978-008045405-4.00163-4

DO - 10.1016/B978-008045405-4.00163-4

M3 - Chapter

AN - SCOPUS:85069568855

VL - 1-5

SP - 245

EP - 254

BT - Encyclopedia of Ecology, Five-Volume Set

PB - Elsevier

ER -

Artificial Neural Networks: Temporal Networks

Abstract

Bibliographical note

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this