About: Performance Analysis of the Activation Neuron Function in the Flexible

Facets (new session)
Description
Metadata
Settings
- owl:sameAs
- Inference Rule:

About: Performance Analysis of the Activation Neuron Function in the Flexible Goto Sponge NotDistinct Permalink

An Entity of Type : http://linked.opendata.cz/ontology/domain/vavai/Vysledek, within Data Space : linked.opendata.cz associated with source document(s)

Attributes	Values
rdf:type	skos:Concept http://linked.opendata.cz/ontology/domain/vavai/Vysledek
rdfs:seeAlso	http://ceur-ws.org/Vol-1139/paper4.pdf
Description	The time series prediction and forecasting is an important area in the field of Machine Learning. Around ten years ago, a kind of Multilayer Neural Network was introduced under the name of Flexible Neural Tree (FNT). This model uses meta-heuristic techniques to determinate its topology and its embedded parameters. The FNT model has been successfully employed on time-series modeling and temporal learning tasks. The activation function used in the FNT belongs to the familyof radial basis functions. It is a parametric function and the parameters are set employing an heuristic procedure. In this article, we analyse the impact on the performance of the FNT model when it used other family of neuron activation functions. For that, we use the hyperbolic tangent and Fermi activation functions on the tree nodes. Both functions have been extensively used in the field of Neural Networks. Moreover, we study the FNT technique with a linear variant of the Fermi function. We present an experimental comparison of our approaches on two widely used time-series benchmarks. The time series prediction and forecasting is an important area in the field of Machine Learning. Around ten years ago, a kind of Multilayer Neural Network was introduced under the name of Flexible Neural Tree (FNT). This model uses meta-heuristic techniques to determinate its topology and its embedded parameters. The FNT model has been successfully employed on time-series modeling and temporal learning tasks. The activation function used in the FNT belongs to the familyof radial basis functions. It is a parametric function and the parameters are set employing an heuristic procedure. In this article, we analyse the impact on the performance of the FNT model when it used other family of neuron activation functions. For that, we use the hyperbolic tangent and Fermi activation functions on the tree nodes. Both functions have been extensively used in the field of Neural Networks. Moreover, we study the FNT technique with a linear variant of the Fermi function. We present an experimental comparison of our approaches on two widely used time-series benchmarks. (en)
Title	Performance Analysis of the Activation Neuron Function in the Flexible Performance Analysis of the Activation Neuron Function in the Flexible (en)
skos:prefLabel	Performance Analysis of the Activation Neuron Function in the Flexible Performance Analysis of the Activation Neuron Function in the Flexible (en)
skos:notation	RIV/61989100:27740/14:86092397!RIV15-MSM-27740___
http://linked.open...avai/riv/aktivita	P
http://linked.open...avai/riv/aktivity	P(ED1.1.00/02.0070), P(EE2.3.30.0055)
http://linked.open...vai/riv/dodaniDat	2015
http://linked.open...aciTvurceVysledku	Basterrech Tiscordio, Sebastian
http://linked.open.../riv/druhVysledku	D - Článek ve sborníku
http://linked.open...iv/duvernostUdaju	S - Úplné a pravdivé údaje nepodléhající ochraně podle zvláštních právních předpisů
http://linked.open...titaPredkladatele	Vysoká škola báňská - Technická univerzita Ostrava / IT4Innovations
http://linked.open...dnocenehoVysledku	36127
http://linked.open...ai/riv/idVysledku	RIV/61989100:27740/14:86092397
http://linked.open...riv/jazykVysledku	eng - angličtina
http://linked.open.../riv/klicovaSlova	Time Series Modeling; Activaction Function; Flexible Neural Tree; Neural Network (en)
http://linked.open.../riv/klicoveSlovo	Activaction Function Time Series Modeling Neural Network Flexible Neural Tree
http://linked.open...ontrolniKodProRIV	[D684613336BB]
http://linked.open...v/mistoKonaniAkce	Roudnice nad Labem
http://linked.open...i/riv/mistoVydani	Aachen
http://linked.open...i/riv/nazevZdroje	CEUR Workshop Proceedings. Volume 1139
http://linked.open...in/vavai/riv/obor	IN
http://linked.open...ichTvurcuVysledku	1 (xsd:int)
http://linked.open...cetTvurcuVysledku	2 (xsd:int)
http://linked.open...vavai/riv/projekt	New creative teams in priorities of scientific research IT4Innovations Centre of Excellence
http://linked.open...UplatneniVysledku	2014
http://linked.open...iv/tvurceVysledku	Basterrech Tiscordio, Sebastian Buriánek, Tomáš
http://linked.open...vavai/riv/typAkce	WRD - Světová
http://linked.open.../riv/zahajeniAkce	2014-05-16 (xsd:date)
issn	1613-0073
number of pages	12 (xsd:int)
http://purl.org/ne...btex#hasPublisher	ceur-ws.org
https://schema.org/isbn	978-80-01-05482-6
http://localhost/t...ganizacniJednotka	27740

Faceted Search & Find service v1.16.118 as of Jun 21 2024

Alternative Linked Data Documents: ODE Content Formats:

RDF

ODATA

Microdata

About

OpenLink Virtuoso version 07.20.3240 as of Jun 21 2024, on Linux (x86_64-pc-linux-gnu), Single-Server Edition (126 GB total memory, 58 GB memory in use)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software