Browsing Theses by Title
Now showing items 8317-8336 of 15526
-
Learn2Perturb: an End-to-end Feature Perturbation Learning to Improve Adversarial Robustness
(University of Waterloo, 2020-08-19)Deep neural networks have been achieving state-of-the-art performance across a wide variety of applications, and due to their outstanding performance, they are being deployed in safety and security critical systems. However, ... -
Learned Legendre Predictive State Estimator for Control
(University of Waterloo, 2022-09-26)This thesis introduces a novel method for system model identification, specifically for state estimation. The method uses a 2 or 3 layer neural network developed and trained with the methods of the Neural Engineering ... -
Learner Beliefs and their Implications for Language Learning
(University of Waterloo, 2006)In this thesis, learner beliefs and their implications for second language learning were examined. Individual learner differences have traditionally been measured statistically by using age, motivation and other variables ... -
Learners' Identity Negotiations and Beliefs about Pronunciation in Study Abroad Contexts
(University of Waterloo, 2011-08-10)This dissertation explores learner beliefs about pronunciation and their interaction with identity negotiations in a study-abroad context. Current research on studying abroad has experienced a wave of interest in ... -
Learning a Motion Policy to Navigate Environments with Structured Uncertainty
(University of Waterloo, 2020-01-24)Navigating in uncertain environments is a fundamental ability that robots must have in many applications such as moving goods in a warehouse or transporting materials in a hospital. While much work has been done on navigation ... -
Learning and Decision Making in Social Contexts: Neural and Computational Models
(University of Waterloo, 2023-04-19)Social interaction is one of humanity's defining features. Through it, we develop ideas, express emotions, and form relationships. In this thesis, we explore the topic of social cognition by building biologically-plausible ... -
Learning and Leveraging Neural Memories
(University of Waterloo, 2018-09-26)Learning in the Neural Engineering Framework (NEF) and the Semantic Pointer Architecture (SPA) has been recently extended beyond the supervised Prescribed Error Sensitivity (PES) to include the unsupervised Vector Oja ... -
Learning Automatic Question Answering from Community Data
(University of Waterloo, 2012-09-19)Although traditional search engines can retrieval thousands or millions of web links related to input keywords, users still need to manually locate answers to their information needs from multiple returned documents or ... -
Learning by Teaching: Key Challenges and Design Implications
(University of Waterloo, 2022-01-17)Benefits of learning by teaching (LbT) have been highlighted by previous studies from a pedagogical lens, as well as through computer-supported systems. However, the challenges that university students face in technology-mediated ... -
Learning Compact Representations for Efficient Whole Slide Image Search in Computational Pathology
(University of Waterloo, 2022-08-24)Digital pathology has enabled us to capture, store, query and analyze scanned biopsy samples as digital images. The widespread adoption of digital pathology has spurred the digitization of tissue biopsy samples, known as ... -
Learning Discriminative Representations for Gigapixel Images
(University of Waterloo, 2022-05-11)Digital images of tumor tissue are important diagnostic and prognostic tools for pathologists. Recent advancement in digital pathology has led to an abundance of digitized histopathology slides, called whole-slide images. ... -
Learning Energy-Aware Transaction Scheduling in Database Systems
(University of Waterloo, 2021-09-20)Servers are typically sized to accommodate peak loads, but in practice, they remain under-utilized for much of the time. During periods of low load, there is an opportunity to save power by quickly adjusting processor ... -
Learning Factors and Determining Document-level Satisfaction In Search-as-Learning
(University of Waterloo, 2017-04-26)An important use of search engines is as a tool for learning. Search engines help users find learning material and increases their knowledge in various topics. The underlying process of learning while web searching and ... -
Learning From Almost No Data
(University of Waterloo, 2021-06-15)The tremendous recent growth in the fields of artificial intelligence and machine learning has largely been tied to the availability of big data and massive amounts of compute. The increasingly popular approach of training ... -
Learning from Chinatown
(University of Waterloo, 2013-04-22)In Learning from Las Vegas, Robert Venturi, Denise Scott Brown, and Steven Izenour approach the city without preconceived opinions because they believe there is something to be learned from every aspect of the built ... -
Learning from Experience to Operationalize Integrated Coastal and Marine Management
(University of Waterloo, 2020-12-16)Integrated coastal and marine management (ICM) is a system of governance that moves beyond traditional sector-based management. ICM is compatible with the holistic vision of a social-ecological systems (SES) approach. ... -
Learning from Green Technology Designers
(University of Waterloo, 2014-02-13)This thesis presents results from a qualitative case study on environmentally minded technology designers, and provides an account of how these designers think, differ and behave. Through semi-structured interviews, we ... -
Learning from Manoomin: Restor(y)ing relationships between Anishinaabeg, settlers, and more-than-human beings in the Great Lakes Basin
(University of Waterloo, 2021-09-20)Positioned between multiple worlds, Manoomin - wild rice is described within the Mishomis Book by the leader and activist Edward Benton Benai, as one of the sacred gifts from the Earth to the Anishinaabeg of the Great Lakes ... -
Learning from Partially Labeled Data: Unsupervised and Semi-supervised Learning on Graphs and Learning with Distribution Shifting
(University of Waterloo, 2007-08-20)This thesis focuses on two fundamental machine learning problems:unsupervised learning, where no label information is available, and semi-supervised learning, where a small amount of labels are given in addition to unlabeled ... -
Learning from the Commonplace: Designing Diversity
(University of Waterloo, 2016-03-03)The commonplace is the realm that directly exists within the ordinary user’s reach and is the everyday lived in experience of the city. Margaret Crawford, the author of Everyday Urbanism, expresses that “an amazing number ...