On the Bayesian Interpretation of Robust Regression Neural Networks

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985807%3A_____%2F24%3A00600652" target="_blank" >RIV/67985807:_____/24:00600652 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1007/978-3-031-72332-2_3" target="_blank" >https://doi.org/10.1007/978-3-031-72332-2_3</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-031-72332-2_3" target="_blank" >10.1007/978-3-031-72332-2_3</a>

Jazyk výsledku

angličtina

Název v původním jazyce

On the Bayesian Interpretation of Robust Regression Neural Networks

Popis výsledku v původním jazyce

The aim of this work is to search for intuitive interpretations of regularized regression procedures within the framework of Bayesian inference. First, the paper considers Bayesian estimation of parameters of the linear regression model. Second, regularized neural networks are explained to correspond to the Bayesian approach obtained under specific assumptions. The contribution is a unique compact look on training neural networks with available prior information, i.e. a likelihood-based perspective of training neural networks. Attention is also paid to very recently proposed regularized versions of robust neural networks, as a novelty, these are expressed by means of quasi-likelihood and their connection to Bayesian reasoning is discussed as well.

Název v anglickém jazyce

On the Bayesian Interpretation of Robust Regression Neural Networks

Popis výsledku anglicky

The aim of this work is to search for intuitive interpretations of regularized regression procedures within the framework of Bayesian inference. First, the paper considers Bayesian estimation of parameters of the linear regression model. Second, regularized neural networks are explained to correspond to the Bayesian approach obtained under specific assumptions. The contribution is a unique compact look on training neural networks with available prior information, i.e. a likelihood-based perspective of training neural networks. Attention is also paid to very recently proposed regularized versions of robust neural networks, as a novelty, these are expressed by means of quasi-likelihood and their connection to Bayesian reasoning is discussed as well.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/GA22-02067S" target="_blank" >GA22-02067S: AppNeCo: Aproximativní neurovýpočty</a><br>

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2024

Kód důvěrnosti údajů

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

Název statě ve sborníku

Artificial Neural Networks and Machine Learning – ICANN 2024. Proceedings Part I

ISBN

978-3-031-72331-5

ISSN

—

e-ISSN

—

Počet stran výsledku

11

Strana od-do

30-40

Název nakladatele

Springer

Místo vydání

Cham

Místo konání akce

Lugano

Datum konání akce

17. 9. 2024

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

001331868600003