Browsing NTNU Open by Author "Kjærnli, Håkon Slåtten"
Now showing items 1-3 of 3
-
Improving the robustness of neural networks for time series forecasting through augmentationswith specific characteristics
Kjærnli, Håkon Slåtten (Master thesis, 2021)Nevrale nettverk er sett på som en toppmoderne metode i mange oppgaver som handler om mønstergjenkjenning, som bildeklassifisering og maskinoversettelse. Likevel har det blitt vist nevrale nettverk ofte produserer prediksjoner ... -
A Machine Learning Classifier for Detection of Physical Activity Types and Postures During Free-Living
Bach, Kerstin; Kongsvold, Atle Austnes; Bårdstu, Hilde Bremseth; Bardal, Ellen Marie; Kjærnli, Håkon Slåtten; Herland, Sverre; Logacjov, Aleksej; Mork, Paul Jarle (Journal article; Peer reviewed, 2021)Accelerometer-based measurements of physical activity types are commonly used to replace self-reports. To advance the field, it is desirable that such measurements allow accurate detection of key daily physical activity ... -
On Reporting Robust and Trustworthy Conclusions from Model Comparison Studies Involving Neural Networks and Randomness
Gundersen, Odd Erik; Shamsaliei, Saeid; Kjærnli, Håkon Slåtten; Langseth, Helge (Chapter, 2023)The performance of neural networks differ when the only difference is the seed initializing the pseudo-random number generator that generates random numbers for their training. In this paper we are concerned with how random ...