A comparison of regularization techniques for shallow neural networks trained on small datasets

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F21%3A10450949" target="_blank" >RIV/00216208:11320/21:10450949 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

A comparison of regularization techniques for shallow neural networks trained on small datasets

Popis výsledku v původním jazyce

Neural networks are frequently used as regression models. Their training is usually difficult when the model is subject to a small training dataset with numerous outliers. This paper investigates the effects of various regularisation techniques that can help with this kind of problem. We analysed the effects of the model size, loss selection, L2 weight regularisation, L2 activity regularisation, Dropout, and Alpha Dropout. We collected 30 different datasets, each of which has been split by ten-fold cross-validation. As an evaluation metric, we used cumulative distribution functions (CDFs) of L1 and L2 losses to aggregate results from different datasets without a considerable amount of distortion. Distributions of the metrics are shown, and thorough statistical tests were conducted. Surprisingly, the results show that Dropout models are not suited for our objective. The most effective approach is the choice of model size and L2 types of regularisations.

Název v anglickém jazyce

A comparison of regularization techniques for shallow neural networks trained on small datasets

Popis výsledku anglicky

Neural networks are frequently used as regression models. Their training is usually difficult when the model is subject to a small training dataset with numerous outliers. This paper investigates the effects of various regularisation techniques that can help with this kind of problem. We analysed the effects of the model size, loss selection, L2 weight regularisation, L2 activity regularisation, Dropout, and Alpha Dropout. We collected 30 different datasets, each of which has been split by ten-fold cross-validation. As an evaluation metric, we used cumulative distribution functions (CDFs) of L1 and L2 losses to aggregate results from different datasets without a considerable amount of distortion. Distributions of the metrics are shown, and thorough statistical tests were conducted. Surprisingly, the results show that Dropout models are not suited for our objective. The most effective approach is the choice of model size and L2 types of regularisations.

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

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2021

Kód důvěrnosti údajů

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

Název statě ve sborníku

CEUR Workshop Proceedings

ISBN

978-981-16-9447-9

ISSN

1613-0073

e-ISSN

—

Počet stran výsledku

10

Strana od-do

94-103

Název nakladatele

CEUR-WS

Místo vydání

Neuveden

Místo konání akce

Nízke Tatry and Muránska planina, Slovakia

Datum konání akce

24. 9. 2021

Typ akce podle státní příslušnosti

EUR - Evropská akce

Kód UT WoS článku

—