Cjevovod za kvantno strojno učenje

master's thesis

• Title (english): Pipeline for quantum machine learning
• Author: Marijo Cvitanović
• Mentor: Mario Brčić (mentor)
• Committee member: Mario Brčić (predsjednik povjerenstva)
• Committee member: Krešimir Fertalj (član povjerenstva)
• Committee member: Nikica Hlupić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2022-07-04, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Podatkovni sustav koji omogućava pouzdano i učinkovito provođenje operacija nad velikim
skupovima podataka se naziva cjevovod. Podržavaju se i izvode operacije od dobave podataka, njihove pred-obrade te za
stvaranje i korištenje modela. Radi pouzdanosti sustava i modela, koristi se prikupljanje dijagnostičkih
podataka o funkcioniranju pojedinih faza u cjevovodu te se statistike prikazuju u prikladnom sučelju da bi
podatkovni inženjer ili podatkovni znanstvenik mogli osiguravati željeni poslovni efekt. U ovom radu je
izrađen cjevovod koji automatizira sve procese vezane za kvantni model strojnog učenja. Od verzioniranja modela do njegovog promatranja. Konstruirana je i objašnjena arhitektura i svaki njen detalj. Naposljetku, modelu, koji je postavljen na Kubernetes grozd, je moguće pristupiti preko REST servisa i dobiti odgovor na postavljeni upit.

Abstract (english)

A pipeline is a data system that enables reliable and efficient operations on large
datasets. Operations from data supply, their pre-processing are supported and performed
creating and using models. For system and model reliability, diagnostic collection is used
on data of individual phases in the pipeline and statistics are displayed in a suitable interface. That interface could provide the desired business effect to
a data engineer or data scientist. In this paper, pipeline was created that can automate the training and use of a separate model of quantum machine learning. The system architecture is constructed and explained which allows execution on a quantum computer as well as on a simulator. Trained and powered can be accessed through the REST service.

• Keywords: Cjevovod; podatci; model; sustav; statistika; sučelje; kvantno strojno učenje; arhitektura
• Keywords (english): Pipeline; data; model; system; statistics; interface; quantum machine learning; architecture
• Language: croatian
• URN:NBN: urn:nbn:hr:168:407220
• Study programme: Title: Computing; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-14 20:13:00