Performance analysis of the activation neuron function in the Flexible Neural Tree model

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27240%2F14%3A86096576" target="_blank" >RIV/61989100:27240/14:86096576 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/61989100:27740/14:86096576

Výsledek na webu

<a href="http://ceur-ws.org/Vol-1139/paper4.pdf" target="_blank" >http://ceur-ws.org/Vol-1139/paper4.pdf</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Performance analysis of the activation neuron function in the Flexible Neural Tree model

Popis výsledku v původním jazyce

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 family of radial basis functions. It isa parametric function and the parameters are set employing an heuristic procedure. In this article, we analyze 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 c

Název v anglickém jazyce

Performance analysis of the activation neuron function in the Flexible Neural Tree model

Popis výsledku anglicky

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 family of radial basis functions. It isa parametric function and the parameters are set employing an heuristic procedure. In this article, we analyze 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 c

Druh

D - Stať ve sborníku

CEP obor

IN - Informatika

OECD FORD obor

—

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2014

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

CEUR Workshop Proceedings. Volume 1139

ISBN

978-80-01-05482-6

ISSN

1613-0073

e-ISSN

—

Počet stran výsledku

12

Strana od-do

35-46

Název nakladatele

ceur-ws.org

Místo vydání

Aachen

Místo konání akce

Roudnice nad Labem

Datum konání akce

16. 5. 2014

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—