Print Email Facebook Twitter Prevalence of non-monotonicity in learning curves Title Prevalence of non-monotonicity in learning curves Author Gafton, Dinu (TU Delft Electrical Engineering, Mathematics and Computer Science) Contributor Viering, T.J. (mentor) Turan, O.T. (mentor) Hung, H.S. (graduation committee) Degree granting institution Delft University of Technology Programme Computer Science and Engineering Project CSE3000 Research Project Date 2024-02-02 Abstract Learning curves are useful to determine the amount of data needed for a certain performance. The conventional belief is that increasing the amount of data improves performance. However, recent work challenges this assumption, and shows nonmonotonic behaviors of certain learners on certain problems. This paper presents a new approach for detecting non-monotonicity in empirical learning curves. This method monitors the degree of monotonicity violation on non-monotonic intervals, using the performance difference. In addition, the accuracy of the algorithm is being assessed through a series of diverse experiments. The proposed algorithm is applied to a subset of the extensive Learning Curve Database (LCDB). The results indicate an experimental accuracy of 95.5% in identifying non-monotonicity within real learning curves. Importantly, the metric demonstrated its ability to distinguish genuine non-monotonic trends from minor fluctuations attributed to measurement errors. Subject Learning curvenon-monotonicityLCDB To reference this document use: http://resolver.tudelft.nl/uuid:76dadd25-3c09-4802-b473-944616360558 Part of collection Student theses Document type bachelor thesis Rights © 2024 Dinu Gafton Files PDF DinuGafton_Final_Paper.pdf 432.66 KB Close viewer /islandora/object/uuid:76dadd25-3c09-4802-b473-944616360558/datastream/OBJ/view