Now showing items 2821-2840 of 3013

    • Towards Data-Leveraged Behavioral Policy Design for Alleviating Peak Electricity Demand 

      Pat, Ankit (University of Waterloo, 2016-01-20)
      The problem of managing peak electricity demand is of significant importance to utility providers. In Ontario, electricity consumption achieves its peak during the afternoon hours in summer. Electricity generation units ...
    • Towards Effective Measurement of Membership Privacy Risk for Machine Learning Models 

      Duddu, Vasisht (University of Waterloo, 2022-07-18)
      Machine learning (ML) models are trained on data which can be sensitive. Membership inference attacks (MIAs) infer whether a particular data record was used to train an ML model. This violates the membership privacy of an ...
    • Towards Effective Utilization of Pretrained Language Models — Knowledge Distillation from BERT 

      Liu, Linqing (University of Waterloo, 2020-09-02)
      In the natural language processing (NLP) literature, neural networks are becoming increasingly deeper and more complex. Recent advancements in neural NLP are large pretrained language models (e.g. BERT), which lead to ...
    • Towards Erdős-Hajnal for Graphs with No 5-Hole 

      Chudnovsky, Maria; Fox, Jacob; Scott, Alex; Seymour, Paul; Spirkl, Sophie (Springer Nature, 2019-11-01)
      The Erdős-Hajnal conjecture says that for every graph H there exists c > 0 such that max(α(G), w(G)) ≥ nc for every H-free graph G with n vertices, and this is still open when H = C5. Until now the best bound known on ...
    • Towards Global Reinforcement Learning 

      Milen, Pavlov (University of Waterloo, 2008-05-14)
      Sequential decision making under uncertainty is a ubiquitous problem. In everyday situations we are faced with a series of decisions that aim to maximize the probability of achieving some goal. However, decision outcomes ...
    • Towards more Effective Censorship Resistance Systems 

      Elahi, Mohammad Tariq (University of Waterloo, 2015-09-29)
      Internet censorship resistance systems (CRSs) have so far been designed in an ad-hoc manner. The fundamentals are unclear and the foundations are shaky. Censors are, more and more, able to take advantage of this situation. ...
    • Towards Object Re-identification from Point Clouds for 3D MOT 

      Thérien, Benjamin (University of Waterloo, 2023-04-21)
      This thesis studies the problem of object re-identification (ReID) in a 3D multi-object tracking (MOT) context, by learning to match pairs of objects from cropped (e.g., using their predicted 3D bounding boxes) point cloud ...
    • Towards Pixel-Level OOD Detection for Semantic Segmentation 

      Angus, Matt (University of Waterloo, 2019-08-30)
      There exists wide research surrounding the detection of out of distribution sample for image classification. Safety critical applications, such as autonomous driving, would benefit from the ability to localise the unusual ...
    • Towards Private Biometric Authentication and Identification 

      Gold, Jonathan (University of Waterloo, 2023-09-05)
      Handwriting and speech are important parts of our everyday lives. Handwriting recognition is the task that allows the recognizing of written text, whether it be letters, words or equations, from given data. When analyzing ...
    • Towards the Efficient Generation of Gray Codes in the Bitprobe Model 

      Frenette, Zachary (University of Waterloo, 2016-05-13)
      We examine the problem of representing integers modulo L so that both increment and decrement operations can be performed efficiently. This problem is studied in the bitprobe model, where the complexity of the underlying ...
    • Towards the Learning, Perception, and Effectiveness of Teachable Conversational Agents 

      Chhibber, Nalin (University of Waterloo, 2019-12-20)
      The traditional process of building interactive machine learning systems can be viewed as a teacher-learner interaction scenario where the machine-learners are trained by one or more human-teachers. In this work, we explore ...
    • Towards Theoretical Foundations of Clustering 

      Ackerman, Margareta (University of Waterloo, 2012-07-20)
      Clustering is a central unsupervised learning task with a wide variety of applications. Unlike in supervised learning, different clustering algorithms may yield dramatically different outputs for the same input sets. As ...
    • Towards Understanding and Improving Code Review Quality 

      Kononenko, Oleksii (University of Waterloo, 2017-06-12)
      Code review is an essential element of any mature software development project, it is key to ensuring the long-term quality of the code base. Code review aims at evaluating code contributions submitted by developers before ...
    • Trace Checking for Dynamic Software Product Lines 

      Olaechea, Rafael; Atlee, Joanne M.; Legay, Axel; Fahrenberg, Uli (ACM, 2018-05)
      A key objective of self-adaptive systems is to continue to provide optimal quality of service when the environment changes. A dynamic software product line (DSPL) can benefit from knowing how its various product variants ...
    • Tracial and ideal structure of crossed products and related constructions 

      Ursu, Dan (University of Waterloo, 2022-08-17)
      In this thesis, we concern ourselves with asking questions about the basic structure of group C*-algebras, crossed products, and groupoid C*-algebras. Specifically, we are concerned with two main topics. One is the simplicity ...
    • Tracing studies in cohorts with attrition: Selection models for efficient sampling 

      Moon, Nathalie C.; Zeng, Leilei; Cook, Richard J. (Wiley, 2018-07-10)
      Cohort studies of chronic diseases involve recruitment and longitudinal followup of affected individuals with a view to studying the effect of risk factors on disease progression and death. When the time to withdrawal from ...
    • Tracking Events in Social Media 

      Tan, Luchen (University of Waterloo, 2017-01-20)
      Tracking topical events in social media streams, such as Twitter, provides a means for users to keep up-to-date on topics of interest to them. This tracking may last a period of days, or even weeks. These events and topics ...
    • Trade-Off Exploration for Acceleration of Continuous Integration 

      Zeng, Zhili (University of Waterloo, 2023-06-21)
      Continuous Integration (CI) is a popular software development practice that allows developers to quickly verify modifications to their projects. To cope with the ever-increasing demand for faster software releases, CI ...
    • Trade-Offs between Fairness, Interpretability, and Privacy in Machine Learning 

      Agarwal, Sushant (University of Waterloo, 2020-05-14)
      Algorithms have increasingly been deployed to make consequential decisions, and there have been many ethical questions raised about how these algorithms function. Three ethical considerations we look at in this work are ...
    • Traffic Rule Checking and Validation 

      Stewart, Connor (University of Waterloo, 2024-02-15)
      This thesis presents a comprehensive exploration of traffic rule verification systems for diverse junction types, addressing key challenges in formalizing rules, determining violation thresholds, and covering a wide spectrum ...

      UWSpace

      University of Waterloo Library
      200 University Avenue West
      Waterloo, Ontario, Canada N2L 3G1
      519 888 4883

      All items in UWSpace are protected by copyright, with all rights reserved.

      DSpace software

      Service outages