• Understanding Minimax Optimization in Modern Machine Learning 

  Zhang, Guojun (University of Waterloo, 2021-07-21)

  Recent years has seen a surge of interest in building learning machines through adversarial training. One type of adversarial training is through a discriminator or an auxiliary classifier, such as Generative Adversarial ...

• Identifying regions of trusted prediction 

  Ananthakrishnan, Nivasini (University of Waterloo, 2021-07-20)

  Quantifying the probability of a label prediction being correct on a given test point or a given sub-population enables users to better decide how to use and when to trust machine learning derived predictors. In this work, ...

• Merlynne: Motivating Peer-to-Peer Cognitive Behavioral Therapy with a Serious Game 

  Chan, Tina; Gauthier, Robert; Suarez, Ally; Sia, Nicholas F.; Wallace, James R (ACM, 2021-09)

  Human-Computer Interaction researchers have explored how online communities can be leveraged for peer support, but general disinterest and a lack of engagement have emerged as substantial barriers to their use in practice. ...

• Nature vs. Stress: Investigating the Use of Biophilia in Non-Violent Exploration Games to Reduce Stress 

  Reetz, Adrian; Valtchanov, Deltcho; Barnett-Cowan, Michael; Hancock, Mark; Wallace, James (ACM, 2021)

  Games hold the potential to help many address health-related issues such as chronic stress. We investigated the use of biophilia, an affective response to nature grounded in the psychology literature, as indirect physiological ...

• Method of Moments in Approximate Bayesian Inference: From Theory to Practice 

  Duan, Haonan (University of Waterloo, 2021-07-12)

  With recent advances in approximate inference, Bayesian methods have proven successful in larger datasets and more complex models. The central problem in Bayesian inference is how to approximate intractable posteriors ...

• Harnessing the Power of Generative Models for Mobile Continuous and Implicit Authentication 

  Tahoun, Ezzeldin (University of Waterloo, 2021-06-30)

  Authenticating a user's identity lies at the heart of securing any information system. A trade off exists currently between user experience and the level of security the system abides by. Using Continuous and Implicit ...

• Signorini conditions for inviscid fluids 

  Gu, Yu (University of Waterloo, 2021-06-28)

  In this thesis, we present a new type of boundary condition for the simulation of inviscid fluids – the Signorini boundary condition. The new condition models the non-sticky contact of a fluid with other fluids or solids. ...

• Continuous Spatial and Temporal Representations in Machine Vision 

  Lu, Thomas (University of Waterloo, 2021-06-02)

  This thesis explores continuous spatial and temporal representations in machine vision. For spatial representations, we explore the Spatial Semantic Pointer as a biologically plausible representation of continuous space ...

• Fast and Scalable Solvers for the Fluid Pressure Equations with Separating Solid Boundary Conditions 

  Lai, Junyu (University of Waterloo, 2021-06-01)

  We propose and evaluate fast, scalable approaches for solving the linear complementarity problems (LCP) arising from the fluid pressure equations with separating solid boundary conditions. Specifically, we present a policy ...

• Mobile Phone Depth Sensors for Forest Carbon Measurement 

  Holcomb, Amelia (University of Waterloo, 2021-05-28)

  The monitoring, reporting, and verification (MRV) of forest plots, especially their tree-trunk diameters, is critical to achieving both forest protection and reforestation goals. Today’s MRV processes are mostly manual, ...

• An Empirical Study on Bash Language Usage in Github 

  Li, Zheyang (University of Waterloo, 2021-05-27)

  The Bourne-again shell (Bash) is a prevalent scripting language for orchestrating shell commands and managing resources in Unix-like environments. At the time of writing, it is one of the mainstream shell dialects that ...

• Knowledge Graph Imputation 

  Niknamian, Mohammadali (University of Waterloo, 2021-05-27)

  Knowledge graphs are one of the most important resources of information in many applications such as question answering and social networks. These knowledge graphs however, are often far from complete as there are so many ...

• Detecting Exploitable Vulnerabilities in Android Applications 

  Sankarapandian, Shivasurya (University of Waterloo, 2021-05-27)

  The world is moving towards remote-first and giving rise to many mobile tools and applications to get the work done. As more applications are moving towards the cloud and therefore require remote access, the attack surface ...

• Supporting Voice-Based Natural Language Interactions for Information Seeking Tasks of Various Complexity 

  Vtyurina, Alexandra (University of Waterloo, 2021-05-25)

  Natural language interfaces have seen a steady increase in their popularity over the past decade leading to the ubiquity of digital assistants. Such digital assistants include voice activated assistants, such as Amazon's ...

• Encrypted Web Traffic Classification Using Deep Learning 

  Akbari Azirani, Iman (University of Waterloo, 2021-05-19)

  Traffic classification is essential in network management for operations ranging from capacity planning, performance monitoring, volumetry, and resource provisioning, to anomaly detection and security. Recently, it has ...

• Scrappy: Using Scrap Material as Infill to Make Fabrication More Sustainable 

  Wall, Ludwig Wilhelm; Jacobson, Alec; Vogel, Daniel; Schneider, Oliver (ACM Press, 2021-05-06)

  We present a software system for fused deposition modelling 3D printing that replaces infill material with scrap to reduce material and energy consumption. Example scrap objects include unused 3D prints from prototyping ...

• A Machine-Learning-Based Algorithm for Peptide Feature Detection from Protein Mass Spectrometry Data 

  Zeng, Xiangyuan (University of Waterloo, 2021-05-13)

  Liquid chromatography with tandem mass spectrometry (LC-MS/MS) has been widely used in proteomics. Two types of data, MS and MS/MS data, are produced in an LC- MS/MS experiment. The MS data contains signal peaks corresponding ...

• A Non-Intersecting R-Tree 

  Langendoen, Kyle Jacob (University of Waterloo, 2021-05-12)

  Indexes for multidimensional data based on the R-Tree are popularly used by databases for a wide range of applications. Such index trees support point and range queries but are costly to construct over datasets of millions ...

• Efficient Data Structures for Partial Orders, Range Modes, and Graph Cuts 

  Sandlund, Bryce (University of Waterloo, 2021-04-30)

  This thesis considers the study of data structures from the perspective of the theoretician, with a focus on simplicity and practicality. We consider both the time complexity as well as space usage of proposed solutions. ...

• In-Network Scheduling for Real-Time Analytics 

  Udayashankar, Sreeharsha (University of Waterloo, 2021-04-30)

  This thesis presents Bolt, a novel scheduler design for large-scale real-time data analytics. Bolt achieves the scheduling accuracy of modern centralized schedulers while supporting clusters with hundreds of thousands of ...

View more