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 34 for “"Deep Learning Architecture"”.
-
Exploiting Novel Deep Learning Architecture in Character Animation Pipelines
… purpose, we describe a variety of cutting-edge deep learning approaches that have been applied to the field of human motion modelling and character animation. The recent advances in motion capture systems and processing hardware have shifted from physics-based approaches to data-driven …
-
A 3D Deep Learning Architecture for Denoising Low-Dose CT Scans
This paper introduces 3D-DDnet, a cutting-edge 3D deep learning (DL) framework designed to improve the image quality of low-dose computed tomography (LDCT) scans. Although LDCT scans are advantageous for reducing radiation exposure, they inherently suffer from reduced image quality. Our novel 3D DL …
-
Computational model for neural architecture search
<p>"A long-standing goal in Deep Learning (DL) research is to design efficient architectures for a given dataset that are both accurate and computationally inexpensive. At present, designing deep learning architectures for a real-world application requires both human expertise and considerable …
-
Seismic Data Processing and Interpretation via Deep Learning
Deep learning (DL) algorithms are growing in popularity in seismic data processing and interpretation due to their efficiency and the ability to deal with non-linear problems. My dissertation focuses on developing new algorithms and workflows for seismic data processing and interpretation by using …
-
Hybrid architecture for human action recognition using skeleton data
In this work, we propose a deep learning architecture, incorporating a Graph Convolutional Network (GCN) backbone combined with a partitioning transformer, that achieves results comparable to the state-of-the-art methods in skeleton based multi-person, multiview human action recognition. By …
-
Biomedical applications of holographic microscopy
… and development. Second, it presents a novel deep-learning architecture that can potentially lower the computational burden of digital holography by replacing existing image reconstruction methods. We demonstrate the effectiveness of the algorithm by reconstructing biological samples and …
-
Empower dynamic scene understanding through scene flow estimation and object segmentation
… dimensionality. This work proposes a lightweight deep learning architecture combining an enhanced Point Transformer for efficient fea- ture extraction and a point-voxel correlation module for sta- ble motion estimation. To bypass labor-intensive object annotations, scene flow is leveraged as …
-
Shared Context through Multi-Level Attention Transformers for Text Classification
… models. Such models tend to be larger, deeper, more complicated; for example, BERT has 340 million parameters, Turing NLG is 17billion parameters, and GPT-3 is about 175 billion parameters. Understanding their implications requires the immense computational ability to process the text …
-
Gait Phase Estimation and Foot Trajectory Prediction During Dynamic Walking Using Gated Recurrent Units
… prediction approach which leverages a recurrent deep learning architecture to make predictions based on sequential walking data. The first of the two ma chine learning models predicts the gait phase as a value between 0 and 1, while the second model leverages the gait phase prediction output to …
-
A CNN–LSTM–Attention Hybrid Architecture for Real-Time Intrusion Detection at the Data Link Layer
… this thesis proposes a memory-efficient hybrid deep learning architecture that integrates Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM) units, and an Attention mechanism for real-time detection of Layer 2 intrusions. A novel dataset, BCCC-DLLayer-IDS-2025, was developed as …
-
Hybrid Distributed Stochastic Gradient Descent for Federated Learning
… environment sets up a perfect playground for deep learning, which is able to utilize the large volumes of data to achieve various tasks. However, as both the volumes of data and the complexity of neural network architecture rises, it becomes increasingly expensive to train the model on a …
-
Applying Flinet Deep Learning Model to Fluorescence Lifetime Imaging Microscopy for Lifetime Parameter Prediction
… These data may be analyzed by FLINET, a deep learning architecture designed specifically for lifetime parameter prediction. The goal of this study is to train the existing FLINET model on synthetic data that best represents FLIM images on UMSCC74A cells exposed to different mitochondrial …
-
Combining numerical simulation and machine learning - modeling coupled solid and fluid mechanics using mesh free methods
… new way to inject the data from simulations into deep learning architecture to aid in the engineering design process. In this thesis the computational mechanics technique, the Material Point Method (MPM) is extended to model the mixed-failure of damage propagation and plasticity in the aggregate …
-
Geo-Informed Deep Learning for Spatial Downscaling of Solute Transport in Heterogeneous Porous Media
… This work proposes a unique two-stage deep learning architecture comprising a dual-branch autoencoder and a Geo-informed super-resolution generative adversarial network (Gi-SRGAN) to address this dual challenge. The dual-branch autoencoder addresses the issue of sparsity by constructing …
-
Determination of the CKM ratio $|V_{ub}|/|V_{cb}|$ using semileptonic $B_c^{+}$ decays at LHCb
… this thesis details the development of a novel deep learning architecture to perform calorimetric shower reconstruction at high energy particle physics experiments. A bespoke network, exploiting recent developments in image recognition and geometric deep learning, is designed to achieve one-shot …
-
Evolving Network Representation Learning Based on Random Walks
… Lately, there is a fast-growing interest in learning low-dimensional continuous representations of networks that can be utilized to perform highly accurate and scalable graph mining tasks. A family of these methods is based on performing random walks on a network to learn its structural …
-
Weak-Supervised Deep Learning Methods for the Analysis of Multi-Source Satellite Remote Sensing Images
… our planet. These data can be analysed by using deep learning methodologies that demonstrate excellent capabilities in extracting the semantics from the data. However, one of the main challenges in exploiting the power of deep learning for remote sensing applications is the lack of labeled …
-
Highly Accurate Fragment Library for Protein Fold Recognition
… living cell. Knowledge of protein folding has a deep impact on understanding the heterogeneity and molecular functions of proteins. Such information leads to crucial advances in drug design and disease understanding. Fold recognition is a key step in the protein structure discovery process, …
-
Enhancing genomic data quality through deep learning methods
… of variants that shed light on the genetic architecture of complex traits. However, the limitations of incomplete genotype data motivated a turn toward imputation. To address this, I introduced STICI, a transformer-based framework that integrates convolutional and attention mechanisms to …
-
Reconfigurability in Wireless Networks: Applications of Machine Learning for User Localization and Intelligent Environment
With the rapid development of machine learning (ML) and deep learning (DL) methodologies, the theoretical foundation of leveraging DL in wireless network reconfigurability and channel modeling is studied and summarized. While deep learning based methods have been applied in a few wireless network …
Page 1 of 2