Training Quantum Restricted Boltzmann Machines Using Dropout Method

Show full item record

Title: Training Quantum Restricted Boltzmann Machines Using Dropout Method
Author: Salmenperä, Ilmo
Contributor: University of Helsinki, Faculty of Science
Publisher: Helsingin yliopisto
Date: 2021
Language: eng
Thesis level: master's thesis
Degree program: Tietojenkäsittelytieteen maisteriohjelma
Master's Programme in Computer Science
Magisterprogrammet i datavetenskap
Specialisation: Tietojenkäsittelyteoria
Theoretical Computer Science
Abstract: Quantum Computing is a novel technology that has wide applicability in the field of machine learning. One of these applications is training Quantum Restricted Boltzmann Machines, which have been shown to have advantages over their classical counterparts. These Quantum Restricted Boltzmann Machines can be then used to pretrain more complex machine learning models, such as Deep Belief Networks, which means that quantum annealing can have applications in the field of deep learning. Main issue of Quantum Restricted Boltzmann Machines is that embedding them into quantum annealing devices will restrict their layer size and connectivity quite drastically. This thesis proposes the use of a common weight regularization method called the unit dropout method to reduce the overall size of these networks by splitting these Restricted Boltzmann Machines into smaller more manageable models, training them separately and composing them into a complete model. While this method can be shown to affect learning negatively, it is yet to be known, whether the advantages of quantum computing can outweigh the disadvantages of extreme use of the unit dropout method.
Subject: Restricted Boltzmann Machines
Deep Belief Networks
Quantum Annealing

Files in this item

Total number of downloads: Loading...

Files Size Format View
Salmenpera_Ilmo_tutkielma_2021.pdf 1.331Mb PDF View/Open

This item appears in the following Collection(s)

Show full item record