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 57 for “"Transformer models"”.
-
Understanding Concept Representations and their Transformations in Transformer Models
As transformer language models continue to be more widely used in a variety of applications, developing methods to understand their internal reasoning processes becomes more critical. One category of such methods called neuron labeling identifies salient directions in the model’s internal …
-
Structural Robustness of Transformer Models for Clinical Text Summarization on MIMIC-III
Transformer-based models are increasingly used to summarize clinical documents, yet their performance is evaluated exclusively on well-formatted text. In practice, clinical notes undergo structural degradation through hospital mergers, EHR migrations, and copy-paste practices, conditions that no …
-
Leveraging Transformer Models and Elasticsearch to Help Prevent and Manage Diabetes through EFT Cues
… predictions. By leveraging Elas- ticsearch and transformer models, this study constructs classifiers and regression models, which can be utilized to identify various content characteristics from the cues. To the best of our knowledge, this work represents the first such attempt to employ natural …
-
AI Enabled Drug Design and Side Effect Prediction Powered by Multi-Objective Evolutionary Algorithms & Transformer Models
Due to the large search space and conflicting objectives, drug design and discovery is a difficult problem for which new machine learning (ML) approaches are required. Here, the problem is to invent a method by which new, therapeutically useful, compounds can be discovered; and to simultaneously …
-
BERT-Based Intrusion Detection System for RF Jamming Attacks in Vehicular Network
… a comprehensive study on the application of transformer-based models for RF jamming detection in intelligent transportation systems. Specifically, we evaluate the performance of four pre-trained transformer architectures—BERT, RoBERTa, DistilBERT, and ALBERT—fine-tuned for the multi-class …
-
Flexible Energy-Aware Image and Transformer Processors for Edge Computing
… techniques to reduce the cost of running these models and provide flexibility in the hardware. Energy scalability is achieved through bit width scaling, as well as model size scaling. These techniques are applied to three neural network accelerators, which have been taped out and tested, to …
-
Machine learning methods for detecting positive selection
… methods, typically employing codon substitution models. These approaches infer rates of nonsynonymous to synonymous substitutions (dN/dS) from nucleotide multiple sequence alignments (MSAs) of homologous, protein-coding genes, interpreted as a proxy for positive selection. These approaches have …
-
Towards Secure and Resilient Machine Learning Systems
… significant breakthroughs is the development of transformer models, which leverage the attention mechanism to achieve state-of-the-art performance across various tasks. Transformers serve as the foundation for commercial large language models (LLMs), such as GPT and Claude, driving progress in …
-
ChaperoNet: Distillation of Language Model Semantics to Folded Three-Dimensional Protein Structures
… been a long-standing goal in biology. Lan- guage models have been recently deployed to capture the evolutionary semantics of protein sequences, and as an emergent property, were found to be structural learn- ers. Enriched with multiple sequence alignments (MSA), these transformer models were able …
-
Using Sports Videos to Showcase Exciting Content to Viewers
… for exciting captions, fine-tune pre-trained transformer models to extract the best sentence from the video clip to use as a caption. Our results show improvements over baselines that solely use emotion-prediction categories of input sentences, suggesting our models are able to learn …
-
Development of a Bagging-based Ensemble Model for ECG Classification
… particularly the application of machine learning models in cardiovascular disease classification and recognition, is rapidly growing. CNN, LSTM, and Transformer models have demonstrated in various studies that, when implemented with robust architectures and supported by ample datasets, they can …
-
Predicting continuous hand pose from wearable EMG sensor data using transformer-based deep-learning models
This thesis investigated Transformer-based deep-learning models for predicting continuous hand pose from electromyography (EMG) signals collected with a low-cost, eight-channel wearable armband. A modular software laboratory was developed to support data acquisition, synchronization, visualization, …
-
De-identification of free-text clinical notes
… of automated de-identification systems. Notably, models built using recurrent neural networks achieved state-of-the-art performance on the de-identification task. Since the competition, new architectures based on transformers have been developed with excellent performance on general domain natural …
-
Empirical Analysis of Neural Architectures and Side Information in Financial Time Series Forecasting
… price data, compare recurrent architectures and transformer-based models, and evaluate multiple training strategies. Our key contributions include: (1) evidence that options-derived input features improve both error metrics and directional accuracy; (2) a comparison study of four training methods …
-
Toward Predictable and Efficient Deep Neural Network Inference on Graphics Processing Units
… local schedulers. Across diverse CNN and Transformer models and workload mixes, the system improves total throughput, tightens P95 and P99 latency, and reduces energy compared to temporal-only, spatial-only, and framework baselines, while preserving deadline behavior. The result is a …
-
Link Prediction on Distributed Systems
… a significant challenge. Traditional static models fail to capture the dynamic nature of these interactions, prompting the use of dynamic graph-based models, such as Graph Neural Networks (GNNs) and transformer-based architectures, for link prediction tasks. Despite their success, these …
-
Combining the Power of Attention Models and Many-objective Computational Intelligence Algorithms for Drug Design
… three objectives. First, it explores the use of Transformer-based models for ADMET prediction based on a hybrid fragment-SMILES tokenization scheme and two training strategies. Second, it evaluates the performance of contrastive Transformer-based latent models for molecular generation. Third, it …
Page 1 of 3