Print Email Facebook Twitter Solving ML with ML: Effectiveness of a star search for synthesizing machine learning pipelines Title Solving ML with ML: Effectiveness of a star search for synthesizing machine learning pipelines Author Lejeune, Rémi (TU Delft Electrical Engineering, Mathematics and Computer Science) Contributor Dumančić, S. (mentor) Hinnerichs, T.R. (mentor) Degree granting institution Delft University of Technology Programme Computer Science and Engineering Project CSE3000 Research Project Date 2023-06-25 Abstract This paper investigates the performance of the A* algorithm in the field of automated machine learning using program synthesis. We designed a context-free grammar to create machine learning pipelines and came up with a cost function for A*. Two different experiments were done, the first one to tune the parameters of our algorithm and the second one to compare the efficiency of A* with other search algorithms. The results indicate that for the selected datasets, A* did not have better performance, but rather had similar results with the other search algorithms. Nevertheless, more research in this field is needed to find concrete results. Subject Machine Learning (ML)Program SynthesisA* search To reference this document use: http://resolver.tudelft.nl/uuid:e6fc0dbe-cb1a-4bec-9894-019afc6144e6 Part of collection Student theses Document type bachelor thesis Rights © 2023 Rémi Lejeune Files PDF CSE3000_Final_Paper_Remi_ ... _FINAL.pdf 206.1 KB Close viewer /islandora/object/uuid:e6fc0dbe-cb1a-4bec-9894-019afc6144e6/datastream/OBJ/view