Theses and Dissertations
This collection contains theses and dissertations of graduate students of the University of Alberta. The collection contains a very large number of theses electronically available that were granted from 1947 to 2009, 90% of theses granted from 2009-2014, and 100% of theses granted from April 2014 to the present (as long as the theses are not under temporary embargo by agreement with the Faculty of Graduate and Postdoctoral Studies). IMPORTANT NOTE: To conduct a comprehensive search of all UofA theses granted and in University of Alberta Libraries collections, search the library catalogue at www.library.ualberta.ca - you may search by Author, Title, Keyword, or search by Department.
To retrieve all theses and dissertations associated with a specific department from the library catalogue, choose 'Advanced' and keyword search "university of alberta dept of english" OR "university of alberta department of english" (for example). Past graduates who wish to have their thesis or dissertation added to this collection can contact us at erahelp@ualberta.ca.
Items in this Collection
- 2Abdi Oskouie, Mina
- 2Birkbeck, Neil Aylon Charles
- 2Cai, Zhipeng
- 2Chen, Jiyang
- 2Chowdhury, Md Solimul
- 2Chubak, Pirooz
- 74Machine Learning
- 70Reinforcement Learning
- 41Artificial Intelligence
- 36Machine learning
- 22Natural Language Processing
- 22Reinforcement learning
-
Spring 2020
In this thesis, we study approximation algorithms for graph pricing where we have a set of items V and a set of customers X where each customer i in X has a budget b(i) and is interested in a bundle of items S(i) subset V with |S(i)| <= 2. However, there is a limited supply of each item: we only...
-
Spring 2011
Grapheme-to-phoneme conversion (G2P) is the task of converting a word, represented by a sequence of graphemes, to its pronunciation, represented by a sequence of phonemes. The G2P task plays a crucial role in speech synthesis systems, and is an important part of other applications, including...
-
Greedification Operators for Policy Optimization: Investigating Forward and Reverse KL Divergences
DownloadFall 2020
Policy gradient methods typically estimate both explicit policy and value functions. The long-extant view of policy gradient methods as approximate policy iteration---alternating between policy evaluation and policy improvement by greedification---is a helpful framework to elucidate algorithmic...
-
Fall 2022
Actor-Critics are a popular class of algorithms for control. Their ability to learn complex behaviours in continuous-action environments make them directly applicable to many real-world scenarios. These algorithms are composed of two parts - a critic and an actor. The critic learns to critique...
-
Spring 2023
Gradient Descent algorithms suffer many problems when learning representations using fixed neural network architectures, such as reduced plasticity on non-stationary continual tasks and difficulty training sparse architectures from scratch. A common workaround is continuously adapting the neural...
-
Fall 2019
DevOps, which stands for Development-Operations, is an important software engineering topic that arose from the IT industry in 2009. XebiaLabs claimed that, in Google Search, DevOps is one of the hottest search terms in technology over the last five years, and continues to rise [1]. According to...
-
Fall 2023
This thesis introduces a new approach for grounding concepts to vision using visual descriptions, which are text-based descriptions of visual attributes. We hypothesize that these descriptions can enhance the grounding of concepts to vision, thereby improving performance in vision-language tasks....
-
Fall 2017
Trip planning queries are considered an important part of Location Based Services. As the first part of our research, we investigated Sequenced Group Trip PLanning Queries (SGTP) queries. Given a set of source locations and destinations for a group of n users, and a sequence of Categories of...
-
Fall 2023
Self-play is a technique for machine learning in multi-agent systems where a learning algorithm learns by interacting with copies of itself. Self-play is useful for generating large quantities of data for learning, but has the drawback that agents the learner will face post-training may have...