Neural Criticality: Validation of Convolutional Neural Networks

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F21%3A43962812" target="_blank" >RIV/49777513:23520/21:43962812 - isvavai.cz</a>

Výsledek na webu

<a href="http://ceur-ws.org/Vol-2808/Paper_36.pdf" target="_blank" >http://ceur-ws.org/Vol-2808/Paper_36.pdf</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Neural Criticality: Validation of Convolutional Neural Networks

Popis výsledku v původním jazyce

The black-box behavior of Convolutional Neural Networks is one of the biggest obstacles to the development of a standardized validation process. Methods for analyzing and validating neural networks currently rely on approaches and metrics provided by the scientific community without considering functional safety requirements. However, automotive norms, such as ISO26262 and ISO/PAS21448, do require a comprehensive knowledge of the system and of the working environment in which the network will be deployed. In order to gain such a knowledge and mitigate the natural uncertainty of probabilistic models, we focused on investigating the influence of filter weights on the classification confidence in Single Point Of Failure fashion. We laid the theoretical foundation of a method called the Neurons’ Criticality Analysis. This method, as described in this article, helps evaluate the criticality of the tested network and choose related plausibility mechanism. Copyright © 2021, for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

Název v anglickém jazyce

Neural Criticality: Validation of Convolutional Neural Networks

Popis výsledku anglicky

The black-box behavior of Convolutional Neural Networks is one of the biggest obstacles to the development of a standardized validation process. Methods for analyzing and validating neural networks currently rely on approaches and metrics provided by the scientific community without considering functional safety requirements. However, automotive norms, such as ISO26262 and ISO/PAS21448, do require a comprehensive knowledge of the system and of the working environment in which the network will be deployed. In order to gain such a knowledge and mitigate the natural uncertainty of probabilistic models, we focused on investigating the influence of filter weights on the classification confidence in Single Point Of Failure fashion. We laid the theoretical foundation of a method called the Neurons’ Criticality Analysis. This method, as described in this article, helps evaluate the criticality of the tested network and choose related plausibility mechanism. Copyright © 2021, for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20205 - Automation and control systems

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

—

ISSN

1613-0073

e-ISSN

—

Počet stran výsledku

9

Strana od-do

—

Název nakladatele

CEUR-WS

Místo vydání

Neuveden

Místo konání akce

Virtual, Online

Datum konání akce

8. 2. 2021

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—