Samodejno strojno učenje znotraj relacijske podatkovne baze PostgreSQL

diplomsko delo

Aljaž Šek (Author), Iztok Fister (Mentor), Grega Vrbančič (Co-mentor)

Abstract

V diplomskem delu smo predstavili in raziskovali uporabnost integracije samodejnega strojnega učenja znotraj relacijske podatkovne baze PostgresSQL. Osredotočili smo se na primerjavo dveh odprtokodnih orodij, ki to integracijo omogočata, in sicer MindsDB in PostgresML, kateri smo primerjali na praktičnem primeru prodaje vozil. Prikazali smo celoten postopek namestitve, povezovanje s podatkovno bazo in uporabo obeh orodij za gradnjo modela strojnega učenja. Raziskali smo glavne razlike med obema orodjema in na koncu predstavili prednosti in slabosti ter ugotovitve primerjave.

Keywords

strojno učenje;samodejno strojno učenje;strojno učenje znotraj relacijskih podatkovnih baz;MindsDB;PostgresML;diplomske naloge;

Data

Language:	Slovenian
Year of publishing:	2024
Typology:	2.11 - Undergraduate Thesis
Organization:	UM FERI - Faculty of Electrical Engineering and Computer Science
Publisher:	[A. Šek]
UDC:	004.85:004.652.4(043.2)
COBISS:	221162499
Views:	0
Downloads:	10
Average score:	0 (0 votes)
Metadata:

Other data

Secondary language:	English
Secondary title:	Automated machine learning within the PostgreSQL relational database
Secondary abstract:	In the thesis, we presented and explored the usability of integrating automated machine learning within the PostgreSQL realtional database. Our main focus was on comparing two open-source tools that enable this integration, namely MindsDB in PostgresML, both of which we compared on a practical example of vehicle sales. We demonstrated the entire process of installation, connection to the database, and the use of both tools for building a machine learning model. We examined the main differences between the two tools and, in the end, presented the advantages and disadvantages as well as the findings of the comparison.
Secondary keywords:	machine learning;automated machine learning;machine learning within a relational database;MindsDB;PostgresML;bachelor's degrees;
Type (COBISS):	Bachelor thesis/paper
Thesis comment:	Univ. v Mariboru, Fak. za elektrotehniko, računalništvo in informatiko, Informatika in tehnologije komuniciranja
Pages:	1 spletni vir (1 datoteka PDF (XI, 66 f.))
ID:	24891053