Browsing Computer Science by Subject "machine learning"
Now showing items 1-20 of 56
-
AdvEx: Interactive Visual Explorations of Adversarial Evasion Attacks
(University of Waterloo, 2023-06-28)Adversarial machine learning (AML) focuses on studying attacks that can fool machine learning algorithms into generating incorrect outcomes as well as the defenses against worst-case attacks to strengthen the adversarial ... -
Analyzing Adversarial Examples: A Framework to Study Adversary Knowledge
(University of Waterloo, 2024-01-22)Adversarial examples are malicious inputs to trained machine learning models supplied to trigger a misclassification. This type of attack has been studied for close to a decade, and we find that there is a lack of study ... -
Analyzing Threats of Large-Scale Machine Learning Systems
(University of Waterloo, 2024-02-22)Large-scale machine learning systems such as ChatGPT rapidly transform how we interact with and trust digital media. However, the emergence of such a powerful technology faces a dual-use dilemma. While it can have many ... -
An Application of Out-of-Distribution Detection for Two-Stage Object Detection Networks
(University of Waterloo, 2020-02-14)Recently, much research has been published for detecting when a classification neural network is presented with data that does not fit into one of the class labels the network learned at train time. These so-called ... -
Automating Programming Assignment Marking with AST Analysis
(University of Waterloo, 2019-01-14)This thesis presents a novel approach to automatically mark programming assignments. We hypothesize that correct student solution ASTs will be more similar to reference solution ASTs than incorrect student solutions and ... -
Bayesian Federated Learning in Predictive Space
(University of Waterloo, 2023-08-10)Federated Learning (FL) involves training a model over a dataset distributed among clients, with the constraint that each client's data is private. This paradigm is useful in settings where different entities own different ... -
BotChase: Graph-Based Bot Detection Using Machine Learning
(University of Waterloo, 2019-05-21)Bot detection using machine learning (ML), with network flow-level features, has been extensively studied in the literature. However, existing flow-based approaches typically incur a high computational overhead and do not ... -
Case Studies of a Machine Learning Process for Improving the Accuracy of Static Analysis Tools
(University of Waterloo, 2016-10-18)Static analysis tools analyze source code and report suspected problems as warnings to the user. The use of these tools is a key feature of most modern software development processes; however, the tools tend to generate ... -
The Computational Advantages of Intrinsic Plasticity in Neural Networks
(University of Waterloo, 2019-10-17)In this work, I study the relationship between a local, intrinsic update mechanism and a synaptic, error-based learning mechanism in ANNs. I present a local intrinsic rule that I developed, dubbed IP, that was inspired by ... -
Contributions to Unsupervised and Semi-Supervised Learning
(University of Waterloo, 2009-05-22)This thesis studies two problems in theoretical machine learning. The first part of the thesis investigates the statistical stability of clustering algorithms. In the second part, we study the relative advantage of ... -
Controlled Generation of Stylized Text Using Semantic and Phonetic Representations
(University of Waterloo, 2022-01-21)Neural networks are a popular choice of models for the purpose of text generation. Variational autoencoders have been shown to be good at reconstructing text and generating novel text. However, controlling certain aspects ... -
Designing a Unity Plugin to Predict Expected Affect in Games Using Biophilia
(University of Waterloo, 2022-09-28)Video games can generate different emotional states and affective reactions, but it can sometimes be difficult for a game’s visual designer to predict the emotional response a player might experience when designing a game ... -
Designing Intelligent Systems to Support Workspace Collaboration
(University of Waterloo, 2023-02-06)Complex problems and interprofessional work require more resources to be involved, which has been possible through collaboration. Collaborative work is evolving from physical collaboration to more virtual forms through ... -
Disentanglement of Syntactic Components for Text Generation
(University of Waterloo, 2022-02-18)Modelling human generated text, i.e., natural language data, is an important challenge in artificial intelligence. A good AI program should be able to understand and analyze natural language, and generate fluent and accurate ... -
Distributions in Semantic Space
(University of Waterloo, 2024-04-26)This thesis is an investigation of the powerful and flexible applications of analyzing empirical distributions of vectors within latent spaces. These methods have historically been applied with great success to the domain ... -
Effects of Developmental Heuristics for Natural Language Learning
(University of Waterloo, 2003)Machine learning in natural language has been a widely pursued area of research. However, few learning techniques model themselves after human learning, despite the nature of the task being closely connected to human ... -
Emotion-Aware and Human-Like Autonomous Agents
(University of Waterloo, 2019-12-20)In human-computer interaction (HCI), one of the technological goals is to build human-like artificial agents that can think, decide and behave like humans during the interaction. A prime example is a dialogue system, where ... -
Entropy-based aggregate posterior alignment techniques for deterministic autoencoders and implications for adversarial examples
(University of Waterloo, 2020-08-27)We present results obtained in the context of generative neural models — specifically autoencoders — utilizing standard results from coding theory. The methods are fairly elementary in principle, yet, combined with the ... -
Exploring Automatic Citation Classification
(University of Waterloo, 2008-05-21)Currently, citation indexes used by digital libraries are very limited. They only provide raw citation counts and link scientific articles through their citations. There are more than one type of citations, but citation ... -
Extracting Non-Functional Requirements from Unstructured Text
(University of Waterloo, 2018-01-18)Non-functional requirements (NFRs) of a software system describe desired quality attributes rather than specific user-visible features; NFRs model stakeholder expectations about pervasive system properties such as performance, ...