Search
Skip to Search Results- 76Rehabilitation
- 37Robotics
- 36Assistive Technology
- 35Reinforcement learning
- 5Exercise
- 5Machine learning
- 59Graduate and Postdoctoral Studies (GPS), Faculty of
- 59Graduate and Postdoctoral Studies (GPS), Faculty of/Theses and Dissertations
- 41Rehabilitation Medicine, Faculty of
- 34Rehabilitation Medicine, Faculty of/General Rehabilitation Medicine
- 6Rehabilitation Medicine, Faculty of/Speech Pathology and Audiology
- 3Computing Science, Department of
- 59Thesis
- 35Article (Draft / Submitted)
- 6Report
- 4Article (Published)
- 2Conference/Workshop Poster
- 2Research Material
-
Fall 2023
Language models are a fundamental component of natural language processing (NLP) systems. Numerous successful deployments of modern artificial intelligence systems are based on language models, including GPT-4 and ChatGPT. In practice, they are often trained with the teacher forcing objective,...
-
EASE-BE-FIT: Elder-Friendly Approaches to the Surgical Environment Bedside Reconditioning for Functional Improvements An Innovative Reconditioning Program for Elderly Emergency Abdominal Surgery Patients
DownloadSpring 2017
Introduction: Elderly individuals who are hospitalized due to emergency abdominal surgery spend on average over 80% of their recovery time in bed, resulting in early and rapid muscle loss. As these elderly individuals have a lower physiological reserve, the impact of muscle wasting on function...
-
Spring 2024
Intracerebral hemorrhage (ICH), a devastating stroke caused by the rupture of vasculature in the brain, is responsible for <20% of all strokes, yet accounts for a disproportionately high burden of stroke related death and disability. The formation and degradation of the hematoma (blood clot)...
-
Fall 2020
This dissertation investigates the properties of representations learned by modern deep reinforcement learning systems. Representation learning plays an important roll in reinforcement learning. A representation contains information extracted from states---the description of the current situation...
-
Establishing Translational Research Pipelines for Smart Devices
2012-09-05
The development of a translational research path has traditionally been a haphazard approach, filtering technologies so that the ‘best of breed’ may ultimately succeed. The conversion ratio of brilliant ideas to useful devices remains suboptimal, as many ‘fail to progress’. The reality of...
-
Fall 2013
This thesis presents new algorithms for dealing with large scale reinforcement learning problems. Central to this work is the Atari 2600 platform, which acts as both a rich evaluation framework and a source of challenges for existing reinforcement learning methods. Three contributions are...