Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 53 for “"feature learning"”.
-
Task-specific and interpretable feature learning
Deep learning models have had tremendous impacts in recent years, while a question has been raised by many: Is deep learning just a triumph of empiricism? There has been emerging interest in reducing the gap between the theoretical soundness and interpretability, and the empirical success of deep …
-
Multiview feature learning for speech recognition
In this thesis, we study the problem of learning a linear transformation of acoustic feature vectors for speech recognition, in a framework where apart from the acoustics, additional views are available at training time. We consider a multiview learning approach based on canonical correlation …
-
Object Tracking: Appearance Modeling And Feature Learning
… algorithm. For re-identification, one or more feature vectors for each tracked object are used</p> <p>after target reappearing. </p> <p>Third, we propose a novel Bayesian Hierarchical Appearance Model (BHAM) for robust object tracking. Our idea is to model the appearance of a target as …
-
Credit card fraud detection using incremental feature learning
… focused on proposing different standard machine learning methods and limited use of incremental learning to create a robust detective system. None of these studies can solve all the credit card fraud challenges together. The reason is the complicated real-world scenario and data we have in our …
-
Application of Prior Information to Discriminative Feature Learning
Learning discriminative feature representations has attracted a great deal of attention since it is a critical step to facilitate the subsequent classification, retrieval and recommendation tasks. In this dissertation, besides incorporating prior knowledge about image labels into the image …
-
Visual feature learning with application to medical image classification
Various hand-crafted features have been explored for medical image classification, which include SIFT and Local Binary Patterns (LBP). However, hand-crafted features may not be optimally discriminative for classifying images from particular domains (e.g. colonoscopy), as not necessarily tuned to …
-
A biological model of object recognition with feature learning
… using idealized scenes and have hard-coded features, such as the HMAX model by Riesenhuber and Poggio [10]. Because HMAX uses the same set of features for all object classes, it does not perform well in the task of detecting a target object in clutter. This thesis presents a new model that …
-
Foundations of Machine Learning: Over-parameterization and Feature Learning
… of neural networks: over-parameterization and feature learning. We leverage these principles to design models with improved performance and interpretability on various computer vision and biomedical applications. We begin by discussing the benefits of over-parameterization, i.e., using …
-
Hardware Acceleration of a Neighborhood Dependent Component Feature Learning (NDCFL) Super-Resolution Algorithm
… based on Neighborhood Dependent Component Feature Learning (NDCFL) is accelerated by multiple GPUs and multiple CPU cores, using NVIDIA’s Computer Unified Device Architecture (CUDA), OpenCV and POSIX threads. Given a low resolution input, this method uses image features to adaptively learn …
-
SnapshotNet: Self-supervised Feature Learning for Point Cloud Data Segmentation Using Minimal Labeled Data
… SnapshotNet is proposed as a self-supervised feature learning approach, which directly works on the unlabeled point cloud data of a complex 3D scene. The SnapshotNet pipeline includes three stages. In the snapshot capturing stage, snapshots, which are defined as local collections of points, …
-
Unsupervised Feature Learning for Point Cloud by Contrasting and Clustering with Graph Convolutional Neural Network
… point cloud datasets, we propose an unsupervised learning approach to learn features from unlabeled point cloud ”3D object” dataset by using part contrasting and object clustering with GNNs. In the contrast learning step, all the samples in the 3D object dataset are cut into two parts and put into …
-
Novel Architectures for Radar Sounder Signals Segmentation: From Convolutional Neural Networks to Quantum-Enhanced Networks
… are grounded in hybrid supervised deep learning architectures, unsupervised feature learning frameworks, and harnessing quantum machine learning frameworks to automatically segment geological units in the cryosphere subsurface. Firstly, we developed a supervised deep learning …
-
Learning sparse features and metric in signal and image processing
This dissertation studies two aspects of feature learning: representation learning and metric in feature space, from a machine learning perspective. Feature learning is a fundamental problem in computer vision and machine learning. First introduced in computational neuroscience in the context of …
-
EFFECTIVE TRAINING OF NEURAL NETWORKS FOR BETTER GENERALIZATION
Deep learning has achieved remarkable success, yet training deep neural networks remains costly, unstable, and poorly understood in terms of generalization. This thesis aims to make training more efficient and generalization-aware, addressing from optimization and data perspectives. From the …
-
Efficient fixed-radius near neighbors for machine learning
Deep learning has enabled artificial intelligence systems to move away from manual feature engineering and toward feature learning and better performance. Convolutional neural networks (CNNs) have especially demonstrated super-human performance in many vision tasks. One big reason for the success …
-
Learning 3D Representations from Data
Deep learning has achieved tremendous progress and success in processing images and natural languages. Deep models enable human-level perception, photorealistic image generation, and conversational language understanding. Despite significant progress, existing deep models still fail to meet the …
-
Spatiotemporal Event Forecasting and Analysis with Ubiquitous Urban Sensors
… neural network for crime prediction, a multitask learning system for traffic incident prediction with spatiotemporal feature learning, social media-based transportation event detection, and a graph convolutional network-based cyberbullying detection algorithm are the four methods proposed. …
-
Unrolling of Graph Total Variation for Image Denoising
While deep learning have enabled effective solutions in image denoising, in general their implementations overly rely on training data and require tuning of a large parameter set. In this thesis, a hybrid design that combines graph signal filtering with feature learning is proposed. It utilizes …
-
Learning Deep Visual Features from Limited Labeled Data
… in order to obtain better performance in visual feature learning for computer vision applications. To reduce the extensive cost of collecting and annotating large-scale labeled datasets, various machine learning methods are proposed to learn general visual features including semi-supervised …
-
Learning from few subjects with large amounts of voice monitoring data
… have started training high complexity machine learning models for clinical tasks, often improving upon previous benchmarks. However, more often than not, these methods require large amounts of supervision to provide good generalization guarantees. When applied to data coming from small cohorts …
Page 1 of 3