Marius Geitle

• Shahraki, Amin; Geitle, Marius & Haugen, Øystein (2020). A comparative node evaluation model for highly heterogeneous massive‐scale Internet of Things‐Mist networks. Transactions on Emerging Telecommunications Technologies. ISSN 1124-318X. 31(12), s. 1–28. doi: 10.1002/ett.3924. Fulltekst i vitenarkiv
• Geitle, Marius & Olsson, Roland (2019). A New Baseline for Automated Hyper-Parameter Optimization. I Nicosia, Giuseppe; Umeton, Renato; Sciacca, Vincenzo; Pardalos, Panos & Giuffrida, Giovanni (Red.), Machine Learning,Optimization,and Data Science - 5th International Conference, LOD 2019. Springer Nature. ISSN 978-3-030-37598-0. s. 521–530. doi: https:/doi.org/10.1007/978-3-030-37599-7_43.
• Tennebø, Frode & Geitle, Marius (2019). Evaluating Population Based Training on Small Datasets. NIKT: Norsk IKT-konferanse for forskning og utdanning. ISSN 1892-0713. Fulltekst i vitenarkiv Vis sammendrag

  Recently, there has been an increased interest in using artificial neural networks in the severely resource-constrained devices found in Internet-of-Things networks, in order to perform actions learned from the raw sensor data gathered by these devices. Unfortunately, training neural networks to achieve optimal prediction accuracy requires tuning multiple hyper-parameters, a process which has traditionally taken many times the computation time of a single training run of the neural network. In this paper, we empirically evaluate the Population Based Training algorithm, a method which simultaneously both trains and tunes a neural network, on datasets of similar size to what we might encounter in an IoT scenario. We determine that the population based training algorithm achieves prediction accuracy comparable to a traditional grid or random search on small datasets, and achieves state-of-the-art results for the Biodeg dataset.

• Shahraki, Amin; Geitle, Marius & Haugen, Øystein (2019). A distributed Fog node assessment model by using Fuzzy rules learned by XGBoost. I Perković, Toni (Red.), 2019 4thInternational Conference on Smart and Sustainable Technologies(SpliTech). IEEE (Institute of Electrical and Electronics Engineers). ISSN 978-953-290-091-0. doi: 10.23919/SpliTech.2019.8783016.
• Geitle, Marius & Olsson, Roland (2017). Using automatic programming to design improved variants of differential evolution. I Bui, Lam Thu (Red.), 2017 21st Asia Pacific Symposium on Intelligent and Evolutionary Systems (IES). IEEE (Institute of Electrical and Electronics Engineers). ISSN 978-1-5386-0743-5. s. 13–18. doi: 10.1109/IESYS.2017.8233554.
• Geitle, Marius & Olsson, Roland (2017). Improving competitive differential evolution using automatic programming. I Fei, Xiang (Red.), 2017 4th International Conference on Systems and Informatics. IEEE (Institute of Electrical and Electronics Engineers). ISSN 978-1-5386-1107-4. s. 538–545. doi: 10.1109/ICSAI.2017.8248350.

Se alle arbeider i Cristin

• Geitle, Marius & Olsson, Roland (2019). A New Baseline for Automated Hyper-Parameter Optimization.
• Shahraki, Amin; Geitle, Marius & Haugen, Øystein (2019). A distributed Fog node assessment model by using Fuzzy rules learned by XGBoost.
• Geitle, Marius (2019). Maskinlæring på Høgskolen i Østfold.
• Geitle, Marius (2018). Hva er Big Data - En introduksjon.
• Geitle, Marius (2018). Lære fra data - Muligheter og utfordringer med maskinlæring.
• Geitle, Marius (2018). Hva er Big Data - En introduksjon.
• Geitle, Marius (2017). Hva er Big Data - En introduksjon.
• Geitle, Marius & Olsson, Roland (2017). Using automatic programming to design improved variants of differential evolution.
• Geitle, Marius & Olsson, Roland (2017). Improving competitive differential evolution using automatic programming.

Se alle arbeider i Cristin