Search
Skip to Search Results- 176Chemistry
- 161Machine Learning
- 100Engineering
- 75Materials Science
- 26Materials science
- 22Artificial Intelligence
- 17Davies, Nicola
- 15Laishram, Devika
- 11Le, Kilara
- 8Musante, Glenna B.
- 8Pelc, Corrie
- 7Wojciechowska, Iza
- 173Graduate and Postdoctoral Studies (GPS), Faculty of
- 173Graduate and Postdoctoral Studies (GPS), Faculty of/Theses and Dissertations
- 101University of Alberta Libraries Licensed Resources
- 101University of Alberta Libraries Licensed Resources/AATCC Review
- 20WISEST Summer Research Program
- 20WISEST Summer Research Program/WISEST Research Posters
-
Fall 2020
This thesis is offered as a step forward in our understanding of forgetting in artificial neural networks. ANNs are a learning system loosely based on our understanding of the brain and are responsible for recent breakthroughs in artificial intelligence. However, they have been reported to be...
-
2017-04-01
Textile products that repel water and stains while retaining breathability have traditionally been made possible through one widely-used type of chemistry, perfluorinated chemicals or, PFCs. These chemicals have also been used in many fire retardants, as well as—most famously—in the “non-stick”...
-
Fall 2022
Sentence reconstruction and generation are essential applications in Natural Language Processing (NLP). Early studies were based on classic methods such as production rules and statistical models. Recently, the prevailing models typically use deep neural networks. In this study, we utilize deep...
-
2015-12-01
Many textile products contain flame retardants to meet flammability or fire safety standards. Flame retardants (FR) inhibit or slow down fire, and thus fulfil a vital role: nobody wants their bed or couch to catch fire and result in flashover. However, research indicates that not all flame...
-
Spring 2020
Reinforcement learning (RL) is a powerful learning paradigm in which agents can learn to maximize sparse and delayed reward signals. Although RL has had many impressive successes in complex domains, learning can take hours, days, or even years of training data. A major challenge of contemporary...
-
Fall 2023
Giving reasons for justifying the decisions made by classification models has received less attention in recent artificial intelligence breakthroughs than improving the accuracy of the models. Recently, AI researchers are paying more attention to filling this gap, leading to the introduction of...
-
2017-08-01
The textile industry affects the environment in many ways, one of which is through the production of wastewater. In particular, effluent (liquid waste discharged into rivers and seas) from factories contains complex chemicals that pollute the environment, and which could prove to be a serious...
-
Spring 2021
This dissertation demonstrates how to utilize data collected previously from different sources to facilitate learning and inference for a target task. Learning from scratch for a target task or environment can be expensive and time-consuming. To address this problem, we make three contributions...
-
Validation and Pattern Discovery in the Canadian Community Health Survey - Mental Health (CCHS-MH) Support Utilization
DownloadSpring 2021
Mental illness is one of the most pressing medical challenges facing society. Although identifying gaps in mental-health support utilization is important for public health, this topic has not been widely explored in the literature. The latest Canadian Community Health Survey - Mental Health...
-
Fall 2019
In this thesis, we investigate different vector step-size adaptation approaches for continual, online prediction problems. Vanilla stochastic gradient descent can be considerably improved by scaling the update with a vector of appropriately chosen step-sizes. Many methods, including AdaGrad,...