20.500.12556/DKUM-95706 Uporabniška izkušnja in zmogljivost platform za strojno učenje: pregled in primerjava pregled in primerjava User experience and performance of machine learning platforms: a review and comparison diplomsko delo V tej diplomski nalogi smo analizirali in primerjali štiri vodilne platforme za strojno učenje: Google Vertex AI, AWS SageMaker, Azure Machine Learning in Databricks. Osredotočili smo se na njihovo zmogljivost pri treniranju modelov, avtomatizaciji procesov ter uporabniško izkušnjo. Uporabili smo tri različne tipe nalog strojnega učenja: klasifikacijo, regresijo in gručen z uporabo ustreznih javno dostopnih podatkovnih zbirk. Testiranja smo izvedli z uporabo Jupyter zvezkov, ročno hiperparametrizacijo in funkcijami AutoML, kar nam je omogočilo primerjavo med različnimi pristopi na vsaki platformi. Na podlagi analize rezultatov ter uporabniških izkušenj smo izpostavili prednosti in slabosti vsake platforme. Ugotovili smo, da je izbira najbolj primerne platforme odvisna od ciljev, tehničnega znanja uporabnika ter specifičnih zahtev projekta. This thesis presents an in-depth analysis and comparison of four leading machine learning platforms: Google Vertex AI, AWS SageMaker, Azure Machine Learning, and Databricks. The focus was placed on evaluating their performance in model training, process automation, and user experience. Three different types of machine learning tasks—classification, regression, and clustering—were explored using relevant publicly available datasets. The evaluation was conducted using Jupyter notebooks, manual hyperparameter tuning, and AutoML functionalities, allowing for a comprehensive comparison of various approaches on each platform. Based on the results and user experience assessments, we highlighted the strengths and weaknesses of each solution. The study concludes that the choice of the most suitable platform largely depends on user expertise, project goals, and technical requirements. strojno učenje platforma za strojno učenje uporabniška izkušnja umetna inteligenca zmogljivost platform za strojno učenje Machine Learning Platforms for machine learning User experience artificial intelligence performance of machine learning platforms true true false [T. Kramberger] Slovenski jezik Angleški jezik Diplomsko delo/naloga 2025-10-13 20:41:40 2025-12-22 09:56:46 2026-02-13 03:12:06 0000-00-00 00:00:00 2025 0 Maribor 0 Maribor 1 spletni vir (1 datoteka PDF (X, 69 str.)) 0000-00-00 NiDoloceno NiDoloceno NiDoloceno 0000-00-00 0000-00-00 0000-00-00 004.85(043.2) 268293379 VS_Kramberger_Tomaz_2025.pdf VS_Kramberger_Tomaz_2025.pdf 1 4368B52E7CADECD00D27325135B9A0F8 2372510de9bc72388cd03b6a12c1954a4b1ecb3935afbb98e476cfcf2b6f7631 d9315a46-a867-11f0-9756-00155d000105 https://dk.um.si/Dokument.php?lang=slv&id=199824 Fakulteta za elektrotehniko, računalništvo in informatiko 0 0 0