Browsing Engineering (Faculty of) by Subject "Deep Learning"
Now showing items 1-20 of 22
-
3D Ground Truth Generation Using Pre-Trained Deep Neural Networks
(University of Waterloo, 2019-05-24)Training 3D object detectors on publicly available data has been limited to small datasets due to the large amount of effort required to generate annotations. The difficulty of labeling in 3D using 2.5D sensors, such as ... -
Bayesian Deep Learning and Uncertainty in Computer Vision
(University of Waterloo, 2019-09-17)Visual data contains rich information about the operating environment of an intelligent robotic system. Extracting this information allows intelligent systems to reason and decide their future actions. Erroneous visual ... -
Computer-Aided Diagnosis for Early Identification of Multi-Type Dementia using Deep Neural Networks
(University of Waterloo, 2017-10-24)With millions of people suffering from dementia worldwide, the global prevalence of this condition has a significant impact on the global economy. As well, its prevalence has a negative impact on patients’ lives and their ... -
Content-based Image Retrieval of Gigapixel Histopathology Scans: A Comparative Study of Convolution Neural Network, Local Binary Pattern, and Bag of visual Words
(University of Waterloo, 2018-05-04)The state-of-the-art image analysis algorithms offer a unique opportunity to extract semantically meaningful features from medical images. The advantage of this approach is automation in terms of content-based image retrieval ... -
Correlated Noise in Deep Convolutional Neural Networks
(University of Waterloo, 2019-08-28)This thesis explores one of the differences between the visual cortex and deep convolutional neural networks, namely, correlated fluctuations of neuron response strength. First, we describe the similarities and differences ... -
Data Balancing and Hyper-parameter Optimization for Machine Learning Algorithms for Secure IoT Networks
(University of Waterloo, 2022-12-19)Nowadays, many industries rely on Machine Learning (ML) algorithms and their ability to learn from existing data to make inferences about new unlabeled data. Applying ML algorithms to the network security domain is not ... -
Deep Learning 3D Scans for Footwear Fit Estimation from a Single Depth Map
(University of Waterloo, 2018-01-02)In clothing and particularly in footwear, the variance in the size and shape of people and of clothing poses a problem of how to match items of clothing to a person. This is specifically important in footwear, as fit is ... -
Deep Learning and Spatial Statistics for Determining Road Surface Condition
(University of Waterloo, 2019-08-28)Machine Learning (ML), and especially Deep Learning (DL) methods, have evolved rapidly over the last years and showed remarkable advances in research areas such as computer vision and natural language processing; however, ... -
Deep Learning Tools for Yield and Price Forecasting Using Satellite Images
(University of Waterloo, 2021-07-26)The ability to forecast crop yields and prices is vital to secure global food availability and provide farmers, retailers, and consumers with valuable information to maximize effectiveness. Conventional approaches used to ... -
Deep Recurrent Neural Networks for Fault Detection and Classification
(University of Waterloo, 2018-12-20)Deep Learning is one of the fastest growing research topics in process systems engineering due to the ability of deep learning models to represent and predict non-linear behavior in many applications. However, the application ... -
A Deep-Learning Framework for Detecting and Predicting Clinical Events Using Continuous, Multimodal Physiological Signals
(University of Waterloo, 2024-02-20)There are an estimated 313 million surgeries performed worldwide each year. Even with significant clinical and technical advances in perioperative research, many patients experience a major complication during the first ... -
Experimental Evaluation of Affordance Detection Applied to 6-DoF Pose Estimation for Intelligent Robotic Grasping of Household Objects
(University of Waterloo, 2021-11-22)Recent computer vision research has demonstrated that deep convolutional neural networks can be trained on real images to add context to object parts for simultaneous object detection and affordance segmentation. However, ... -
Generative Thermal Design Through Boundary Representation and Deep Reinforcement Learning
(University of Waterloo, 2022-09-08)Advancement in Additive Manufacturing (AM) allows fabrication of complex geometries. This provides the opportunity to think beyond hand-designed topologies. The main goal of this dissertation is to build a Generative Design ... -
Large-Scale Traffic Flow Prediction Using Deep Learning in the Context of Smart Mobility
(University of Waterloo, 2018-04-24)Designing and developing a new generation of cities around the world (termed as smart cities) is fast becoming one of the ultimate solutions to overcome cities' problems such as population growth, pollution, energy crisis, ... -
Multimodal Artificial Intelligence for Histopathology & Genomics Fusion
(University of Waterloo, 2024-01-29)The field of medical diagnostics has witnessed a transformative convergence of artificial intelligence (AI) and healthcare data, offering promising avenues for enhancing patient care and disease comprehension. However, ... -
New Convolutional Neural Network Topology with Compressed Information to Enhance Accuracy for Image Classification Task
(University of Waterloo, 2019-09-23)Source coding and deep learning are two major branches in the field of information processing. Source coding encodes information that can be summarised with patterns into certain representation without semantic consideration. ... -
Parallelizing Legendre Memory Unit Training
(University of Waterloo, 2021-07-14)Recently, a new recurrent neural network (RNN) named the Legendre Memory Unit (LMU) was proposed and shown to achieve state-of-the-art performance on several benchmark datasets. Here we leverage the linear time-invariant ... -
Real-time 3D Object Detection for Autonomous Driving
(University of Waterloo, 2018-05-10)This thesis focuses on advancing the state-of-the-art 3D object detection and localization in autonomous driving. An autonomous vehicle requires operating within a very unpredictable and dynamic environment. Hence a robust ... -
Receiver Channel Recovery in High-Frame-Rate Ultrasound Imaging using Branched Convolutional Neural Networks
(University of Waterloo, 2022-08-22)High frame rate ultrasound (HiFRUS) is an imaging paradigm that utilizes unfocused transmissions to perform acquisitions at kilohertz frame rates, and its high temporal resolution enables its use in tracking dynamic ... -
Regularizing Deep Models for Visual Recognition
(University of Waterloo, 2016-10-26)Image understanding is a shared goal in all computer vision problems. This objective includes decomposing the image into a set of primitive components through which one can perform region segmentation, region labeling, ...