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 99 for “"Transformer Architectures"”.
-
Modular Power Converters for Smart Transformer Architectures
… power quality and reliability. The Smart Transformer (ST) has emerged as a technology able to solve most of these problems, providing a compact and efficient solution. Several Smart Transformer architectures have been discussed in literature. The three stages architecture (composed by a …
-
Latent-Space Engineering and Modular Transformer Architectures for Efficient Multimodal Intelligence
… a systematic investigation of a lightweight, transformer-inspired engine designed to achieve high-throughput inference across heterogeneous signal domains without the prohibitive computational overhead typical of modern Vision Transformers (ViTs). Chapter 3 establishes the foundational Binary …
-
12-Lead Electrocardiogram Anomaly Detection Using Hybrid 1D and 2D CNN+Transformer Architectures
… 1D convolutional neural networks (CNNs) with a transformer and another combining 2D CNNs with a transformer. The multilabel PTB-XL dataset includes over 21,000 cardiovascular conditions grouped into five superclasses: myocardial infarction, conduction disturbances, hypertrophy, ST-T wave …
-
Novel Transformer Architectures For 3d Multi-Modal And Multi-Organ Medical Image Segmentation
… specifically focusing on the integration of transformers and convolutional neural networks (CNNs) for enhanced medical image segmentation. The primary goal is to improve segmentation accuracy and efficiency in clinical settings, particularly for CT and MRI images. The dissertation is …
-
High-efficiency control, protection, and modulation strategies for modular medium-voltage solid-state transformer architectures
… changes in power conversion systems. Solid-State Transformers (SSTs) offer a promising pathway by enabling compact, efficient, and controllable interfacing with the Medium-Voltage (MV) grid without traditional bulky line-frequency transformers. However, their realization involves overcoming …
-
Adaptive Stock Market Prediction Using Node Transformer Architectures with Sentiment Analysis and Reinforcement Learning Control
… statistical models and standard deep learning architectures, typically treat stocks as independent time series and process all market conditions through a single model, limiting their capacity to capture cross-sectional structure and adapt to regime shifts. This thesis develops a series of …
-
Contextual AI: Integrating Macro-Context with Transformer Architectures for Social Media Analysis, Federated Learning, and Recommender Systems
… and making informed decisions. While existing transformer architectures excel at contextualizing information locally, such as other words in a sentence, they fail to factor in broader, macro-level contexts. We identify available yet underutilized macro contexts in three use cases: online …
-
Improve Vehicle Efficiency Accuracy Through Virtual Sensors - A Comparative Study of MLP, LSTM, and Transformer Architectures with and without Physics-Informed Constraints for Fuel Consumption Prediction
… (MLP), Long Short-Term Memory (LSTM), and Transformer architectures are evaluated to determine the most suitable model for this scenario, while the impact of incorporating Physics-informed Neural Networks (PINNs) on prediction performance is also investigated. Using historical field test …
-
Examining Information Flows Within Transformer Models Using Transfer Entropy
… neural networks. This is especially true for transformer architectures and large language models, which are the driving force behind the current surge in artificial intelligence. The complexity of transformer architecture foils many pre-existing methods for studying explainability in deep …
-
Giliaisiais neuroniniais tinklais grįstų kalbos modelių charakteristikos analizė mažos imties duomenų rinkiniuose /
This work analyzes transformer language model performance under low sample size datasets. Multiple autoencoder transformer models: BERT, RoBERTa, ELECTRA with their base and large configurations are applied and trained on selected datasets. Multilingual XLM-R and mBERT models are evaluated under …
-
Physics-Informed Transfer Learning for Process Control
… foundation, the research advances to incorporate transformer architectures combined with Physics-Informed Neural Networks (PINNs) to quantify the effects of transfer learning for system identification and surrogate control modeling in data-scarce environments. The physics-informed transfer …
-
Toward Transformer-based Large Energy Models for Smart Energy Management
… be developed using large-scale datasets. Transformer architectures, known for their scalability, ability to capture long-term dependencies, and efficiency in parallel processing of large datasets, are considered good candidates for GEMs. In this study, we tested the hypothesis that GEMs …
-
Private data navigation with localized ai-based chatbot /
… Augmented Generation (RAG) systems, leveraging transformer architectures and vector databases. This work describes the RAG structure and deployment options, maintaining the system’s operations independent of cloud platforms. The experiments assess the system’s response to 100 questions, which …
-
Optimization Strategies for Enhancing Resource Efficiency in Transformers & Large Language Models
… Language Processing are heavily reliant on Transformer architectures, whose improvements come at substantial resource costs due to ever-growing model sizes. This study explores optimization techniques, including quantization, knowledge distillation, and pruning, focusing on energy and …
-
Novel ad text generation for real estate
Transformer architectures have brought unreasonable progress to natural language generation in recent years. However, generating high quality and relevant advertising text is difficult. Inspired by Laban et. al., reinforcement learning is used in this paper to encourage a generative pretrained …
-
BRIDGING GRAPH-STRUCTURED DATA AND LARGE LANGUAGE MODELS
… and represents them as sequences compatible with Transformer architectures. Third, G-Retriever retrieves task-relevant subgraphs based on natural language queries, encodes them with GNNs, and injects the resulting representations into LLMs as soft prompts for structure-aware generation. Together, …
-
Towards Interpretable Scene Understanding through Parsing and Attention
… the proliferation of large-scale datasets, novel architectures, and sophisticated training techniques. However, despite these strides, the challenge of developing models that not only achieve high performance but also offer interpretable insights into their decision-making processes remains a …
-
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, …
Page 1 of 5