Detail publikace

Physics-informed ML models for processing of spectroscopic data

VRÁBEL, J. KÉPEŠ, E. POŘÍZKA, P. KAISER, J.

Originální název

Physics-informed ML models for processing of spectroscopic data

Typ

abstrakt

Jazyk

angličtina

Originální abstrakt

Massive adoption of machine learning (ML) techniques in spectroscopy brought entirely new possibilities in analytical performance for applications, and also for basic research. However, several problems emerged, e.g. ML models are often utilized as “black-boxes”, or considerably overtrained. Another issue is a blind transition of successful models (architecture, parameters) from distinct applications (e.g. image processing) to spectroscopic tasks, without taking into account the properties of data. We study the influence of (spectroscopic) data properties and incorporate them into ML models in form of weight initializations, specific parameter penalizations, and invariances. This leads to an increased analytical performance of models and better interpretability.

Klíčová slova

machine learning, interpretability, spectroscopic data, neural networks, deep learning

Autoři

VRÁBEL, J.; KÉPEŠ, E.; POŘÍZKA, P.; KAISER, J.

Vydáno

24. 8. 2021

BibTex

@misc{BUT172427,
  author="Jakub {Vrábel} and Erik {Képeš} and Pavel {Pořízka} and Jozef {Kaiser}",
  title="Physics-informed ML models for processing of spectroscopic data",
  year="2021",
  note="abstract"
}