RegNeN 2012

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21110%2F12%3A00200395" target="_blank" >RIV/68407700:21110/12:00200395 - isvavai.cz</a>

Result on the web

<a href="http://klobouk.fsv.cvut.cz/~anicka/regnen/regnen.html" target="_blank" >http://klobouk.fsv.cvut.cz/~anicka/regnen/regnen.html</a>

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

RegNeN 2012

Original language description

Program for finding optimal regression function of given data using artificial neural network (ANN). The implemented ANN architecture is based on fully connected three-layer perceptron. It offers the choice between two training algorithms, the deterministic conjugate gradient-based algorithm and the stochastic Covariance Matrix Adaptation Evolution Strategy (CMA-ES). The software can normalize the training and testing data according to the specification in the input file. The user has to supply it by the training and testing data. During the training phase, the number of hidden neurons is automatically increased and overtraining is evaluated by the cross-validation method. The resulting best topology is then evaluated on the provided independent testing data.

Czech name

—

Czech description

—

Type

R - Software

CEP classification

JD - Use of computers, robotics and its application

OECD FORD branch

—

Project

<a href="/en/project/GPP105%2F11%2FP370" target="_blank" >GPP105/11/P370: Artificial neural networks in multi-scale modelling of transport processes in heterogeneous materials</a><br>

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year

2012

Confidentiality

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

Internal product ID

RegNeN 2012

Technical parameters

verze v C++

Economical parameters

volně k dispozici

Owner IČO

68407700

Owner name

Fakulta stavební ČVUT v Praze