Search

2021-08-01

Irene Olayinka, Calarina Muslimani, Dr. Matthew Taylor

Although this report deals with the mechanisms of artificially intelligent rather than intelligence agents, the former is no less a subject of fascination. My research centred around an algorithm called Training an Agent Manually via Evaluative Reinforcement (TAMER), which incorporates human...

Fall 2019

Benoit, James RA

The goal of this thesis is to contribute to the fields of data-driven medicine and computational psychiatry by attempting to demonstrate the viability of machine learning for use in psychiatry, specifically in predicting treatment outcomes for major depression. This is attempted in four ways: ...

Spring 2020

Schumacker Soares, Everton

Several Artificial Intelligence (AI) techniques such as machine learning, evolutionary computing, and Artificial Life (A-life) have been increasingly used to generate emergence of novel behaviours in multi-agent simulations (e.g., commercial games). However, automatically detecting emergent...

Spring 2021

Bennett, Brendan

Temporal difference (TD) methods provide a powerful means of learning to make predictions in an online, model-free, and highly scalable manner. In the reinforcement learning (RL) framework, we formalize these prediction targets in terms of a (possibly discounted) sum of rewards, called the...

Fall 2018

Althubaiti, Majed

The objective of this work is to design a scheme to control the power flow of a hybrid renewable energy system with multiple renewable energy sources with the focus on solar energy and wind energy and multiple energy storage systems. The use of energy storage is necessary due to the intermittency...

Fall 2020

Chan, Alan

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...

2020

Gill, Jasmine Kaur

Healthcare Fraud is an act that causes a loss of billions of dollars every year across the world. The impact of healthcare fraud is very far-reaching and affects the efficiency of healthcare systems. To thwart the perpetrators early on, intelligent fraud detection technologies are required to...

2020-08-06

Popowich, Sam

Academic libraries have recently seen a shift from self-management of user-authentication of licensed resources themselves, to cloud-based implementations of "federated identity" technologies. Such technologies aim to solve the problems of fragile access to licensed resources while also better...

Spring 2021

Narvey, Rachel

This thesis explores how the couple form is represented in four filmic objects: Her (2013), Bladerunner 2049 (2017), Ex Machina (2015), and “Be Right Back,” an episode of the TV series Black Mirror. I will argue that each of these films demonstrate that the couple fixates on the discreteness...