Search
Skip to Search Results- 85Artificial Intelligence
- 39Learning
- 22Machine Learning
- 10Reinforcement Learning
- 9Education
- 9Planning
- 69Graduate and Postdoctoral Studies (GPS), Faculty of
- 69Graduate and Postdoctoral Studies (GPS), Faculty of/Theses and Dissertations
- 18Computing Science, Department of
- 18Computing Science, Department of/Technical Reports (Computing Science)
- 11Toolkit for Grant Success
- 8Toolkit for Grant Success/Successful Grants (Toolkit for Grant Success)
- 69Thesis
- 22Report
- 15Research Material
- 5Conference/Workshop Poster
- 4Article (Published)
- 4Conference/Workshop Presentation
-
Scalable Solutions to Image Abnormality Detection and Restoration using Limited Contextual Information
DownloadFall 2020
Detecting and interpreting image abnormalities and restoring images are essential to many processing pipelines in diverse fields. Challenges involved include randomness and unstructured nature of image artefacts (from signal processing perspective) and performance constraints imposed by...
-
Spring 2020
Two-Player alternate-turn perfect-information zero-sum games have been suggested as a testbed for Artificial Intelligence research since Shannon in 1950s. In this thesis, we summarize and develop algorithms for this line of research. We focus on the game of Hex — a game created by Piet Hein in...
-
Fall 2023
Many works of art are created through the process of an artist sketching and then incrementally increasing the fidelity of the artwork. This requires significant amounts of work and effort throughout, but not all steps require the same amount of artistic input. Certain parts only require...
-
Fall 2014
Designing competitive Artificial Intelligence (AI) systems for Real-Time Strategy (RTS) games often requires a large amount of expert knowledge (resulting in hard-coded rules for the AI system to follow). However, aspects of an RTS agent can be learned from human replay data. In this thesis, we...
-
Strengths, Weaknesses, and Combinations of Model-based and Model-free Reinforcement Learning
DownloadSpring 2016
Reinforcement learning algorithms are conventionally divided into two approaches: a model-based approach that builds a model of the environment and then computes a value function from the model, and a model-free approach that directly estimates the value function. The first contribution of this...
-
2011
Technical report TR11-01. Causality is a fundamental concept in reasoning. The effectiveness of many reasoning tasks depends on the understanding of the underlying cause-effect relationships. Therefore, the notion of causality has been explored in a wide range of disciplines. Causal discovery,...
-
2009
Faculty in Canadian undergraduate nursing programs have come to rely on preceptorship as the primary model for teaching and learning during the final clinical course. A focused ethnography was completed in order to examine undergraduate nursing students’ experience of rural hospital preceptorship...
-
Fall 2013
Given nothing but the generative model of the environment, Monte Carlo Tree Search techniques have recently shown spectacular results on domains previously thought to be intractable. In this thesis we try to develop generic techniques for temporal abstraction inside MCTS that would allow the...
-
Spring 2018
Teaching portfolios have been used by faculty in postsecondary institutions for summative and formative evaluations since the early 1980s (Knapper, 1995). Despite their proliferation, there remains much to be learned about the use of teaching portfolios and whether they are perceived as being...