diplomsko delo
Tim Dizdarević (Author), Matjaž Kukar (Mentor)

Abstract

Umetna inteligenca je postala nepogrešljiva na področju podatkovnih tehnologij. Omogoča gradnjo ter uporabo izjemno natančnih modelov za napovedovanje, s katerimi si lahko pomagamo pri sprejemanju pomembnih odločitev. Cilj diplomske naloge je predstaviti uporabo avtomatiziranega strojnega učenja v sodobnih sistemih za upravljanje podatkovnih baz s študijo primera MindsDB, poglobitev v izzive strojnega učenja, prikaz uporabe velikih jezikovnih modelov ter s koraki CRISP-DM implementirati in uporabiti napovedne modele na raznovrstnih podatkovnih virih. Rezultate kvantitativno primerjamo tudi s tradicionalnimi tehnikami strojnega učenja. MindsDB je pokazal uspešnost in vsestranskost pri različnih nalogah napovednega modeliranja ter sposobnost vključevanja velikih jezikovnih modelov, kar kaže na uporabnost v različnih scenarijih.

Keywords

MindsDB;strojno učenje;napovedni modeli;CRISP-DM;avtomatizirano strojno učenje;univerzitetni študij;diplomske naloge;

Data

Language: Slovenian
Year of publishing:
Typology: 2.11 - Undergraduate Thesis
Organization: UL FRI - Faculty of Computer and Information Science
Publisher: [T. Dizdarević]
UDC: 004.85(043.2)
COBISS: 228258819 Link will open in a new window
Views: 99
Downloads: 20
Average score: 0 (0 votes)
Metadata: JSON JSON-RDF JSON-LD TURTLE N-TRIPLES XML RDFA MICRODATA DC-XML DC-RDF RDF

Other data

Secondary language: English
Secondary title: Automated machine learning inside database management systems
Secondary abstract: Artificial intelligence has become indispensable in the field of data technologies. It allows us to build and use highly accurate predictive models that help us make important decisions. The aim of this thesis is to present the use of automated machine learning in modern database management systems, with a case study of MindsDB. The thesis delves into the challenges of machine learning, demonstrates the use of large language models, and applies predictive models to diverse data sources using the CRISP-DM methodology. The results are quantitatively compared with traditional machine learning techniques. MindsDB has demonstrated success and versatility across various predictive modeling tasks, as well as the ability to integrate large language models, highlighting its usefulness in different scenarios.
Secondary keywords: MindsDB;machine learning;predictive models;CRISP-DM;automated machine learning;computer and information science;diploma;
Type (COBISS): Bachelor thesis/paper
Study programme: 1000468
Embargo end date (OpenAIRE): 1970-01-01
Thesis comment: Univ. v Ljubljani, Fak. za računalništvo in informatiko
Pages: 1 spletni vir (1 datoteka PDF (132 str.))
ID: 25980387