Browsing Computer Science by Subject "machine learning"
Now showing items 21-40 of 56
-
FJMP: Factorized Joint Multi-Agent Motion Prediction
(University of Waterloo, 2023-08-30)Multi-agent motion prediction is an important problem in an autonomous driving pipeline, and it involves forecasting the future behaviour of multiple agents in complex driving environments. Autonomous vehicles (AVs) should ... -
From Atoms to the Solar System: Generating Lexical Analogies from Text
(University of Waterloo, 2006)A <em>lexical analogy</em> is two pairs of words (<em>w</em><sub>1</sub>, <em>w</em><sub>2</sub>) and (<em>w</em><sub>3</sub>, <em>w</em><sub>4</sub>) such that the relation between <em>w</em><sub>1</sub> and <em>w</em>< ... -
Fundamental Limitations of Semi-Supervised Learning
(University of Waterloo, 2009-05-05)The emergence of a new paradigm in machine learning known as semi-supervised learning (SSL) has seen benefits to many applications where labeled data is expensive to obtain. However, unlike supervised learning (SL), which ... -
Future Sight: Dynamic Story Generation with Large Pretrained Language Models
(University of Waterloo, 2022-08-23)Automated story generation has been an open problem in computing for many decades. Only with the recent wave of deep learning research have neural networks been applied to automated story generation tasks. Current deep ... -
A General Neural Network Methodology for Multi-period Portfolio Optimization
(University of Waterloo, 2024-01-22)In this thesis, we propose a neural network methodology for solving the multi-period portfolio optimization problem. Our approach formulates the problem as a stochastic optimal control problem and uses a single neural ... -
Graph-Based Spatial-Temporal Cluster Evolution: Representation, Analysis, and Implementation
(University of Waterloo, 2023-08-28)Spatial-temporal data are information about real-world entities that exist in a location, the spatial dimension, and during a period of time, the temporal dimension. These real-world entities, such as vehicles, people, or ... -
Halfway to Halfspace Testing
(University of Waterloo, 2017-10-18)In this thesis I study the problem of testing halfspaces under arbitrary probability distributions, using only random samples. A halfspace, or linear threshold function, is a boolean function f : Rⁿ → {±1} defined as the ... -
Improved Bayesian Network Structure Learning in the Model Averaging Paradigm
(University of Waterloo, 2023-01-10)A Bayesian network (BN) is a probabilistic graphical model with applications in knowledge discovery and prediction. Its structure can be learned from data using the well-known score-and-search approach, where a scoring ... -
JITGNN: A Deep Graph Neural Network for Just-In-Time Bug Prediction
(University of Waterloo, 2022-05-10)Just-In-Time (JIT) bug prediction is the problem of predicting software failure immediately after a change is submitted to the code base. JIT bug prediction is often preferred to other types of bug prediction (subsystem, ... -
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, ... -
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 Sample-Based Monte Carlo Denoising from Noisy Training Data
(University of Waterloo, 2022-02-15)Monte Carlo rendering allows for the production of high-quality photorealistic images of 3D scenes. However, producing noise-free images can take a considerable amount of compute resources. To lessen this burden and speed ... -
Learning-Free Methods for Goal Conditioned Reinforcement Learning from Images
(University of Waterloo, 2021-04-27)We are interested in training goal-conditioned reinforcement learning agents to reach arbitrary goals specified as images. In order to make our agent fully general, we provide the agent with only images of the environment ... -
Likelihood-based Density Estimation using Deep Architectures
(University of Waterloo, 2019-12-20)Multivariate density estimation is a central problem in unsupervised machine learning that has been studied immensely in both statistics and machine learning. Several methods have thus been proposed for density estimation ... -
A Machine Learning Approach for RDP-based Lateral Movement Detection
(University of Waterloo, 2019-09-19)Detecting cyber threats has been an on-going research endeavor. In this era, advanced persistent threats (APTs) can incur significant costs for organizations and businesses. The ultimate goal of cybersecurity is to thwart ... -
Machine Learning for Streamflow Prediction
(University of Waterloo, 2020-04-16)Accurate prediction of streamflow—the amount of water flowing past a stream section at a given time—is a long-standing challenge in hydrology. Not only do researchers strive to understand the natural processes at play, the ... -
MLOD: A multi-view 3D object detection based on robust feature fusion method
(University of Waterloo, 2019-09-19)This thesis presents Multi-view Labelling Object Detector (MLOD). The detector takes an RGB image and a LIDAR point cloud as input and follows the two-stage object detection framework. A Region Proposal Network (RPN) ... -
Model-Based Bayesian Sparse Sampling for Data Efficient Control
(University of Waterloo, 2019-06-24)In this work, we propose a novel Bayesian-inspired model-based policy search algorithm for data efficient control. In contrast to other model-based approaches, our algorithm makes use of approximate Gaussian processes in ... -
MT-MAG: Accurate and interpretable machine learning for complete or partial taxonomic assignments of metagenome-assembled genomes
(University of Waterloo, 2022-05-19)We propose MT-MAG, a novel machine learning-based software tool for the complete or partial hierarchically-structured taxonomic classification of metagenome-assembled genomes (MAGs). MT-MAG is capable of classifying large ... -
Multilingual Grammatical Error Detection And Its Applications to Prompt-Based Correction
(University of Waterloo, 2024-01-05)Grammatical Error Correction (GEC) and Grammatical Error Correction (GED) are two important tasks in the study of writing assistant technologies. Given an input sentence, the former aims to output a corrected version of ...