[HTML][HTML] The role of metadata in reproducible computational research

J Leipzig, D Nüst, CT Hoyt, K Ram, J Greenberg - Patterns, 2021 - cell.com
Reproducible computational research (RCR) is the keystone of the scientific method for in
silico analyses, packaging the transformation of raw data to published results. In addition to …

[PDF][PDF] Semantic web technologies for explainable machine learning models: A literature review.

A Seeliger, M Pfaff, H Krcmar - PROFILES/SEMEX@ ISWC, 2019 - researchgate.net
Due to their tremendous potential in predictive tasks, Machine Learning techniques such as
Artificial Neural Networks have received great attention from both research and practice …

Generic digital twin architecture for industrial energy systems

G Steindl, M Stagl, L Kasper, W Kastner, R Hofmann - Applied Sciences, 2020 - mdpi.com
Digital Twins have been in the focus of research in recent years, trying to achieve the vision
of Industry 4.0. In the domain of industrial energy systems, they are applied to facilitate a …

Blockchain and federated learning-based intrusion detection approaches for edge-enabled industrial IoT networks: A survey

S Ali, Q Li, A Yousafzai - Ad Hoc Networks, 2024 - Elsevier
The industrial internet of things (IIoT) is an evolutionary extension of the traditional Internet of
Things (IoT) into processes and machines for applications in the industrial sector. The IIoT …

A step toward quantifying independently reproducible machine learning research

E Raff - Advances in Neural Information Processing …, 2019 - proceedings.neurips.cc
What makes a paper independently reproducible? Debates on reproducibility center around
intuition or assumptions but lack empirical results. Our field focuses on releasing code …

Provenance data in the machine learning lifecycle in computational science and engineering

R Souza, L Azevedo, V Lourenço… - 2019 IEEE/ACM …, 2019 - ieeexplore.ieee.org
Machine Learning (ML) has become essential in several industries. In Computational
Science and Engineering (CSE), the complexity of the ML lifecycle comes from the large …

dtoolai: Reproducibility for deep learning

M Hartley, TSG Olsson - Patterns, 2020 - cell.com
Deep learning, a set of approaches using artificial neural networks, has generated rapid
recent advancements in machine learning. Deep learning does, however, have the potential …

Toward a Practical Digital Twin Platform Tailored to the Requirements of Industrial Energy Systems

L Kasper, F Birkelbach, P Schwarzmayr, G Steindl… - Applied Sciences, 2022 - mdpi.com
Digitalization and concepts such as digital twins (DT) are expected to have huge potential to
improve efficiency in industry, in particular, in the energy sector. Although the number and …

Machine learning pipelines: provenance, reproducibility and FAIR data principles

S Samuel, F Löffler, B König-Ries - International Provenance and …, 2020 - Springer
Abstract Machine learning (ML) is an increasingly important scientific tool supporting
decision making and knowledge generation in numerous fields. With this, it also becomes …

A semantic framework to support AI system accountability and audit

I Naja, M Markovic, P Edwards, C Cottrill - … 2021, Virtual Event, June 6–10 …, 2021 - Springer
To realise accountable AI systems, different types of information from a range of sources
need to be recorded throughout the system life cycle. We argue that knowledge graphs can …