Opening black-box models used in LIBS

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26620%2F21%3APU142521" target="_blank" >RIV/00216305:26620/21:PU142521 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Opening black-box models used in LIBS

Popis výsledku v původním jazyce

The use of multivariate data-based models has become synonymous with modern LIBS analysis, be it qualitative or quantitative [1]. Two of such techniques frequently found in the LIBS literature are support vector machines (SVM) and artificial neural networks, namely convolutional neural networks (CNNs). While both techniques have undoubtedly contributed to achieving state-of-the-art classification performance in several LIBS applications, there is a common drawback associated with both methods, namely their black-box nature. In this work, we carried out the post-hoc interpretation of SVM and CNN models trained for a classification task. SVM classifiers were interpreted via the determination of feature importances [2]. The CNNs were interpreted by finding the optimal input spectra that maximize the activation of individual convolutional neurons and by carrying out class activation maximization [3]. The latter technique finds the input spectra that best represent the classes learnt by the network. We fou

Název v anglickém jazyce

Opening black-box models used in LIBS

Popis výsledku anglicky

The use of multivariate data-based models has become synonymous with modern LIBS analysis, be it qualitative or quantitative [1]. Two of such techniques frequently found in the LIBS literature are support vector machines (SVM) and artificial neural networks, namely convolutional neural networks (CNNs). While both techniques have undoubtedly contributed to achieving state-of-the-art classification performance in several LIBS applications, there is a common drawback associated with both methods, namely their black-box nature. In this work, we carried out the post-hoc interpretation of SVM and CNN models trained for a classification task. SVM classifiers were interpreted via the determination of feature importances [2]. The CNNs were interpreted by finding the optimal input spectra that maximize the activation of individual convolutional neurons and by carrying out class activation maximization [3]. The latter technique finds the input spectra that best represent the classes learnt by the network. We fou

Druh

O - Ostatní výsledky

CEP obor

—

OECD FORD obor

10406 - Analytical chemistry

Projekt

<a href="/cs/project/GJ20-19526Y" target="_blank" >GJ20-19526Y: Procesy laserové ablace měkkých tkání a následného vývoje laserem buzeného plazmatu</a><br>

Návaznosti

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

Rok uplatnění

2021

Kód důvěrnosti údajů

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