Primjena metoda strojnog učenja za kvantna računala

undergraduate thesis

• Title (english): Application of Machine Learning Methods for Quantum Computers
• Author: Jan Ljubas
• Mentor: Goran Delač (mentor)
• Committee member: Goran Delač (predsjednik povjerenstva)
• Committee member: Marin Kačan (član povjerenstva)
• Committee member: Helena Čeović (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2023-07-05, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Glavna tema ovog završnog rada su metode strojnog učenja primjenjive za kvantna računala. Cilj rada je proučiti koje su metode trenutno ostvarive za izvršavanje na postojećim kvantnim računalima i kako hibridni klasično-kvantni algoritmi pospješuju dosadašnje klasične algoritme.
Za prikaz programskog kôda i simulacije izabran je IBM-ov open-source SDK za programiranje kvantnih računala, Qiskit. [3]
Glavninu rada čini pregled metoda strojnog učenja za koje postoje kvantni pandani [6]. Poseban naglasak stavlja se na programsku potporu za kvantne neuronske mreže i na kvantni SVM (na klasifikaciju i regresiju pomoću ansatza). Kroz kôd pisan u Qiskitu detaljno se opisuju postupci i teorijska podloga koja omogućava iskorištavanje prednosti kvantnih računala nad klasičnim računalima. Prikaz (teorijskih, simuliranih) rezultata napravljen je dijagramima i tablicama.

Abstract (english)

The main topic of this bachelor's thesis are machine learning methods applicable for quantum computers. The objective is to study the methods which are applicable on the existing or the near-term quantum computers and explore how the hybrid quantum-classical algorithms (in theory) enhance traditional, classical algorithms.

Implementing the quantum algorithms and running simulations was done using Qiskit, IBM's open-source SDK. [3]
The bulk of the paper consists of an overview of the well-known machine learning methods and their quantum counterparts [6]. In Chapters 3 and 4, special emphasis is placed on quantum neural networks implementation and quantum support vector machines(SVM) (or solving the classification and regression problems using variational quantum circuits). Along with the Qiskit code, the description of theoretical foundations behind it is provided.
The simulated results are presented through diagrams and tables.

• Keywords: strojno učenje; kvantno strojno učenje; kvantna računala; QNN; neuronske mreže
• Keywords (english): machine learning; quantum machine learning; quantum computers; QNN; neural networks
• Language: croatian
• URN:NBN: urn:nbn:hr:168:050504
• Study programme: Title: Computing; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-10-11 09:35:43