FFG COMET Center for Integrated Computational Materials, Process and Product Engineering (COMET IC-MPPE)

Research Grant
2022-2024
Research Grant

Summary: This project is a collaboration with the Materials Center Leoben (MCL), who is coordinating this effort, and a couple of partner institutions, including University of Technology, Graz, Austria. The main research question is how to use machine learning techniques for industrial condition monitoring with the main goal to extend lifetime of machinery by continuous monitoring and assessment of state. Within this collaboration we are most concerned with finding resource-efficient neural networks to make them inline with embedded systems close to the point of interest.

While the first phase (2018-2021) was mainly considering state-of-the-art neural networks for the prediction task, such as convolutional or residual ones, in the second phase (2022-2024) the focus shifted to probabilistic models to also capture uncertainty.

The project has received funding by “Österreichische Forschungsförderungsgesellschaft mbH (FFG)”, Austria.

Current people

  • Holger Fröning (co-PI)
  • Bernhard Klein (PhD student)
  • Tamara Bucher (master student)

Past people

  • Lisa Kuhn (master student)
  • Falk Selker (master student)
  • Jonathan Bernhard (bachelor student)
  • Torben Krieger (master student)
  • Florian Brunner (master student)

Collaborators

  • Manfred Mücke (MCL, co-PI)
  • Christoph Gratl (MCL, researcher)
  • Franz Pernkopf (University of Technology, Graz, Austria, co-PI)
  • Sophie Steger (University of Technology, Graz, Austria, PhD student)

Contact

Dissemination

2024

  1. Wolfgang Roth, Günther Schindler, Bernhard Klein, Robert Peharz, Sebastian Tschiatschek, Holger Fröning, Franz Pernkopf and Zoubin Ghahramani
    Resource-Efficient Neural Networks for Embedded Systems
    Journal of Machine Learning Research, 25(50), 1–51, 2024
    link | arXiv | bib 
    @article{JMLR:v25:18-566,
  author = {Roth, Wolfgang and Schindler, G{{\"u}}nther and Klein, Bernhard and Peharz, Robert and Tschiatschek, Sebastian and Fr{{\"o}}ning, Holger and Pernkopf, Franz and Ghahramani, Zoubin},
  title = {Resource-Efficient Neural Networks for Embedded Systems},
  journal = {Journal of Machine Learning Research},
  year = {2024},
  volume = {25},
  number = {50},
  pages = {1--51},
  url = {http://jmlr.org/papers/v25/18-566.html},
}
  2. Sophie Steger, Christian Knoll, Bernhard Klein, Holger Fröning and Franz Pernkopf
    Function Space Diversity for Uncertainty Prediction via Repulsive Last-Layer Ensembles
    ICML 2024 Workshop on Structured Probabilistic Inference & Generative Modeling, 2024
    link | bib 
    @inproceedings{steger2024function,
  title = {Function Space Diversity for Uncertainty Prediction via Repulsive Last-Layer Ensembles},
  author = {Steger, Sophie and Knoll, Christian and Klein, Bernhard and Fr{\"o}ning, Holger and Pernkopf, Franz},
  booktitle = {ICML 2024 Workshop on Structured Probabilistic Inference {\&} Generative Modeling},
  year = {2024},
  url = {https://openreview.net/forum?id=FbMN9HjgHI},
}

2022

  1. Torben Krieger, Bernhard Klein and Holger Fröning
    Towards Hardware-Specific Automatic Compression of Neural Networks
    CoRR, abs/2212.07818, 2022
    link | bib 
    @article{DBLP:journals/corr/abs-2212-07818,
  author = {Krieger, Torben and Klein, Bernhard and Fr{\"{o}}ning, Holger},
  title = {Towards Hardware-Specific Automatic Compression of Neural Networks},
  journal = {CoRR},
  volume = {abs/2212.07818},
  year = {2022},
  url = {https://arxiv.org/abs/2212.07818},
  doi = {10.48550/ARXIV.2212.07818},
  eprinttype = {arXiv},
  eprint = {2212.07818},
  timestamp = {Mon, 02 Jan 2023 00:00:00 +0100},
}

2021

  1. Bernhard Klein, Christoph Gratl, Manfred Mücke and Holger Fröning
    Understanding Cache Boundness of ML Operators on ARM Processors
    CoRR, abs/2102.00932, 2021
    link | bib 
    @article{DBLP:journals/corr/abs-2102-00932,
  author = {Klein, Bernhard and Gratl, Christoph and M{\"{u}}cke, Manfred and Fr{\"{o}}ning, Holger},
  title = {Understanding Cache Boundness of {ML} Operators on {ARM} Processors},
  journal = {CoRR},
  volume = {abs/2102.00932},
  year = {2021},
  url = {https://arxiv.org/abs/2102.00932},
  eprinttype = {arXiv},
  eprint = {2102.00932},
  timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
}