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 504 for “"Deep learning algorithms"”.
-
Asymptotic analysis of deep learning algorithms
<p>We investigate the asymptotic properties of deep residual networks as the number of layers increases. We first show the existence of scaling regimes for trained weights markedly different from those implicitly assumed in the neural ODE literature. We study the convergence of the hidden state …
-
Speech enhancement by using deep learning algorithms
… Over the past decade, the advent of deep learning has catalysed remarkable progress in the field of speech enhancement. With the proliferation of smart devices demanding real-time processing capabilities, the development of real-time deep learning-based speech enhancement systems has …
-
Deep learning algorithms for cardiovascular image analysis
Deep Learning technologies are creating a revolution in the analysis of medical images. We are getting closer to the vision of a fully automated and reliable characterization of disease, both reproducing what the expertise of the radiologist is trained for, and proposing new metrics, revealing new …
-
Deep learning algorithms for semantic and instance segmentation
… the study, development and application of Deep learning architectures on the most important and widely applicable field areas: semantic segmentation, document binarization, and instance segmentation. A strong emphasis is given on efficient, low complexity architectures that strike a balance …
-
Deep learning algorithms for age-related macular degeneration
Radboud University, 21 september 2022
-
Methodology for applying deep learning algorithms for glaucoma identification /
… develops a multi-level methodology for applying deep learning (DL) algorithms to automate glaucoma detection, while addressing key challenges related to expert annotation variability, dataset inconsistencies, and the lack of standardised diagnostic thresholds. A comprehensive analysis of …
-
Loom and Laconic: Hardware Accelerators for Deep Learning Algorithms
… does not require intervention from the Machine Learning expert; however, it rewards optimizations such as pruning and quantization. Laconic benefits from approximation techniques that reduce the constituent powers of two used to represent a number.
-
Deep Learning Algorithms for Cardiopulmonary Image and Signal Analysis
… listening abilities and experiences. Designing algorithms for accurately recognizing abnormal heart sounds is thus indispensable. Besides, modern screening tools like chest X-ray (CXR) and computed tomography (CT) can retrieve high-resolution images of patients that reveal multiple organ …
-
Data Efficient Deep Learning Algorithms for Video Processing Systems
Over the last decade, deep neural networks have grown in popularity and became the standard approach for the majority of computer vision tasks. Their ability to deliver state of the art results without involving carefully designed hand-crafted features is unmatched, however, that strong performance …
-
Understanding and improving numerical stability of deep learning algorithms
Deep learning (DL) has become an integral part of solutions to various important problems, which is why ensuring the quality of DL systems is essential. One of the challenges of achieving reliability and robustness of DL software is to ensure that algorithm implementations are numerically stable. …
-
Deep learning algorithms and architectures for natural language processing
This dissertation explores the development of deep neural networks training algorithms and architectures which can be utilized in real world Natural Language Processing (NLP) tasks. To this end, we develop a novel constrained optimization framework that incorporates a-priori knowledge in the …
-
Deep learning algorithms for background subtraction and people detection
… researched to date and the top-performing algorithms are data-driven and supervised. Crucially, during training these algorithms rely on the availability of some annotated frames from the video being tested. Instead, we propose a novel, supervised background-subtraction algorithm for unseen …
-
SIGN LANGUAGE RECOGNIZER FRAMEWORK BASED ON DEEP LEARNING ALGORITHMS
… novel sign language recognition framework using deep neural networks, which directly maps videos of sign language sentences to sequences of gloss labels by emphasizing critical characteristics of the signs and injecting domain-specific expert knowledge into the system. The proposed model also …
-
Identifying Smokestacks in Remotely Sensed Imagery via Deep Learning Algorithms
… of automating this process, this thesis examines deep learning networks and how changes in input datasets and network architecture affect image detection accuracy. This initial image detection serves as the first step in automated object recognition and height calculation. While this is applicable …
-
Cross Scanner Breast Adenocarcinoma Image Segmentation with Deep Learning Algorithms
… σης (VFM), ενσωματωμένο στην αρχιτεκτονική του DeepLabv3+. Για την αντιμετώπιση ε- μποδίων, όπως η περιορισμένη διαθεσιμότητα δεδομένων και οι διαφοροποιήσεις μεταξύ σαρωτών, εφαρμόστηκαν εκτεταμένες μέθοδοι επαύξησης εικόνων. Επιπλέον, πραγμα- τοποιήθηκε συστηματική αξιολόγηση διαφορετικών …
-
Developing Informatics Frameworks for Evaluating Deep Learning Algorithms for Mammography
Deep learning algorithms have played a major role in advancing AI for mammography-based breast cancer screening. Studies have shown that AI tools can achieve, and in some cases exceed, the performance of breast imaging radiologists. Integrating deep learning algorithms into clinical workflows has …
-
Prediction of travel time using deep learning algorithms to solve TDVRPTW
… three groups: statistical methods, basic machine learning methods, and deep learning methods. In this project, we apply deep learning algorithms to predict travel time accurately. By leveraging the power of Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), and Temporal …
-
DATA SET GENERATION USING DEEP LEARNING ALGORITHMS AND VISUAL FEATURE TRACKING
… sets for every specific application of these algorithms. In this report, a method for generating image data sets with the use of visual feature tracking and deep learning algorithms for application in autonomous vehicles has been proposed. The aim is to reduce the time and effort dedicated …
-
Probabilistic and Deep Learning Algorithms for the Analysis of Imagery Data
… these issues, we need to devise intelligent learning algorithms which require a deep understanding and careful analysis of the feature space. In this thesis, we introduce three new learning frameworks for the analysis of both airborne images (NAIP dataset) and handwritten digit datasets …
Page 1 of 26