Development of machine learning techniques and evaluation of analysis results

Stefanos Kollias, Andreas Stafylopatis, Georgios Leontidis, Georgios Alexandridis, Tatiana Tabouratzis, Aiden Durrant

Research output: Other contribution

10 Downloads (Pure)


This document outlines and describes the development of deep neural network architectures and other machine learning techniques for the unfolding of reactor transfer functions from in-core and ex-core neutron detectors, developed in CORTEX Workpackage 3, mainly in Task 3.3. The techniques developed utilise simulated modelling of the induced neutron flux of perturbations to classify and localise perturbation types and their sources.
Original languageEnglish
PublisherEuropean Commission
Number of pages42
Publication statusPublished - 12 Aug 2019

Bibliographical note

CORTEX - Research and Innovation Action (RIA)
This project has received funding from the European
Union's Horizon 2020 research and innovation programme
under grant agreement No 754316.


  • nuclear reactors
  • Machine learning


Dive into the research topics of 'Development of machine learning techniques and evaluation of analysis results'. Together they form a unique fingerprint.

Cite this