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 1848 for “"Deep learning models"”.
-
TRANSFERABILITY OF DEEP LEARNING MODELS
Transferability in deep learning models is of great significance as it aims to improve the performance of models in diverse scenarios. In the study of Out-of-Distribution Generalization (OOD), we deeply analyze the model's generalization ability to out-of-domain data and clarify its inherent …
-
Contributions to Deep Learning Models
[EN] Deep Learning is a new area of Machine Learning research which aims to create computational models that learn several representations of the data using deep architectures. These methods have become very popular over the last few years due to the remarkable results obtained in speech …
-
Adversarial Robustness of Deep Learning Models
Deep neural networks (DNNs) have demonstrated remarkable success across various machine learning tasks but remain highly vulnerable to adversarial perturbations. Adversarial training (AT) and its variants aim to enhance robustness by incorporating adversarial examples into training. However, AT …
-
Decomposing deep learning models into modules
Deep learning-based software is prevalently being utilized in various applications, i.e., image classification, autonomous driving, and medical analysis. To build these models, developers collect data, craft the architecture of the model, and finally, train the model with the available data. To …
-
Protein Characterization using Deep Learning Models
… structure. Recent advances in protein language models, large-scale reference databases, and structure prediction methods have created new opportunities to characterize proteins using multiple complementary data modalities. Although this dissertation explores specific biological applications, the …
-
Deep Learning Models for CT Image Standardization
… address this issue, we present four end-to-end deep-learning-based models for CT image standardization and normalization. The first two models require paired training data and can standardize images acquired from the same scanner but with different non-standardized protocols. The third model …
-
Dairy profitability prediction using deep learning models
Dans la gestion de précision de l’élevage, une prise de décision efficace concernant le remplacement des animaux dépend d’une estimation précise de la rentabilité à vie de chaque animal. En production laitière, la quantité de lait produite est influencée par divers facteurs, notamment la qualité du …
-
Robustness and safety of deep learning models.
Deep learning (DL) refers to a data-driven machine learning technique in which neural networks with many layers are used to model and understand complex patterns and relationships in the data. DL models have revolutionized numerous complex real-world tasks ranging from image recognition to natural …
-
Efficient deep learning models for video abstraction
… Firstly, we develop fully convolutional sequence deep learning models that address the computational limitations of the previous deep learning models for video abstraction. Secondly, we propose a new formulation of unpaired training data for the model learning to reduce the need of expensive …
-
Classification of brainwaves using deep learning models
… many recent studies. In all the results, the CNN models outperform the FFT and Fully Connected Network results by a significant margin. This comparison also sheds light on certain signal characteristics affecting the model's performance.
-
UNDERSTANDING FAILURE MODES OF DEEP LEARNING MODELS
In the past few years, deep learning models have advanced significantly, achieving remarkable results in challenging problems across multiple domains such as vision and language. Despite their proficiency, these models exhibit numerous failure modes and intriguing behaviors that cannot be mitigated …
-
Investigating Distribution Shifts for Deep Learning Models
<p>Machine learning, specifically deep learning with Deep Neural Networks (DNNs), has revolutionized many fields and enabled the accurate execution of various complex tasks, including those in the field of computer vision and natural language processing, to name just a few. The great success of …
-
TROPICAL GEOMETRIC APPROACHES TO DEEP LEARNING MODELS
… applications of piecewise linear operators in deep learning architectures, which have been published or submitted in a series of journal and conference proceedings articles. The tropical algebra, descriptively called max-plus algebra, replaces smooth Euclidean operators with maximization and …
-
Finding Influential Examples in Deep Learning Models
Machine learning models are powerful, but not without errors and the complexity of large models makes it hard for a human to intuitively understand the cause of the error. This thesis approaches the task of explaining predictions made by deep learning models by studying the importance of specific …
-
Analysis of storage bottlenecks in Deep Learning models
Deep Learning (DL) is gaining prominence and is widely used for a plethora of problems. DL models, however, take in the order of days to train. Optimizing hyper-parameters is another factor that adds to the training time. This thesis aims to analyze the training pattern on Convolutional Neural …
-
IMPROVING ATTENTION-BASED DEEP LEARNING MODELS WITH LOCALITY
Recent attention-based deep learning models adopt a transformer architecture that uses attention mechanism to figure out which part of the input the model should be concerned. Notably, these models outperform traditional CNN and RNN-based methods significantly. However, due to the permutation …
-
Marine mammal sound classification using deep learning models
… current solutions based on traditional machine learning technologies face challenges in classifying a diverse range of marine mammal sounds with high accuracy. This study aims to improve classification accuracy for marine mammal vocalizations by refining the feature vectors from sounds, …
-
Deep learning models for mobile and wearable biometrics
… awareness. However, these high-performing models require significant computational resources, making their deployment on resource-constrained smartphones challenging. To address this challenge, studies have proposed compact-size ocular-based deep-learning models for on-device deployment. In …
-
Continual Learning and Forgetting in Deep Learning Models
Continual learning is a framework of learning in which we aim to move beyond the limitations of standard isolated optimization of deep learning models toward a more intelligent setting, where models or agents are able to accumulate skills and knowledge, across diverse tasks and over extended …
Page 1 of 93