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 12 of 12 for “"GPT-2"”.
-
Assessing text readability and quality with language models
… on 7 out of 9 datasets. We demonstrate that GPT-2 surpasses other language models, including the bigram model, LSTM, and bidirectional LSTM, on the task of estimating text quality in a zero-shot setting, and GPT-2 perplexity-based measure is a reasonable indicator for text quality evaluation.
-
Evaluating Large Language Models for Turboshaft Engine Torque Prediction
… the performance of four different models: GPT-2 and ChatGPT (general-purpose LLMs), TimeGPT (a specialized transformer-based model for time series data), and a conventional time series transformer model. The models are assessed on a real-world dataset derived from a Bell 407 helicopter’s …
-
Transformer Pruning Relation and General Neural Network Augmentation
… testing loss against density was found for the GPT-2 transformer network on a causal language modeling task. An interesting double plateau of testing loss was found whenever the attention weights were pruned. Next, augmentation on low dimensional datasets and shallow networks was investigated. …
-
Assessing the memorability of familiar vocabulary for system assigned passphrases
… with the Generative Pre-trained Transformer 2 (GPT-2) model trained on the familiar vocabulary and are readable, pronounceable, sentence like passphrases resembling natural English sentences. Contrary to expectations, following a spaced repetition schedule, passphrases as natural English …
-
Generování stylizovaného lidského jazyka v dialogových systémech
… nejmodernější předpřipravené modely BART a GPT-2 pro generování textu. Experimenty odhalily problém, že i současné nejmodernější modely trpí špatným odhadem kompromisu mezi stylem a kontextem. Jinými slovy, čím více se styl projeví v generované sekvenci, tím méně se vztahuje k tématu …
-
Study on Adversarial Robustness of Phishing Email Detection Models
… phishing emails are generated using a fine-tuned GPT-2 model. The detection model has retrained with newly formed dataset and we have observed the accuracy and robustness of the model has not improved under black box attack methods. In our last experiment we proposed a defensive technique to …
-
AutoDiff: A Scalable Framework for Automated Model Comparison
… report. Proof-ofconcept experiments on GPT-2 small validate AutoDiff’s ability to rediscover synthetic perturbations without manual supervision. A larger case study on Llama3.1–8B contrasts the base model with several adapted variants, surfacing neurons whose behavioral shifts align with …
-
Contextual Predictability and Phonetic Reduction
… making use of such models. We train instances of GPT-2 on different context directions (past, future, and bidirectional) and context sizes (bigram vs. sentence) to provide measures of conditional word predictability, then use linear regression to quantify their correlation with a measure of …
-
Automated and Provable Privatization for Black-Box Processing
… large language models (LLM), such as ResNet and GPT-2, and hardware security, such as side-channel cache-timing leakage control.
-
Knowledge Augmentation in Language Models to Overcome Domain Adaptation and Scarce Data Challenges in Clinical Domain
… of Generative Pretrained Transformer (GPT)-2 and Bidirectional Encoder Representations from Transformers (BERT) that uses knowledge graphs to inject domain knowledge for domain adaptation tasks. The end goal of this chapter is to reduce the training time and improve the performance of …
-
Detecting Zero-Day Attacks in IEC-61850 based Digital Substations via In-Context Learning
The occurrences of cyber attacks, with novel attack techniques, on the electrical power grids have been increasing every year. In this thesis, we address the critical challenge of detecting novel/zero-day attacks in digital substations that employ the IEC-61850 communication protocol. While many …
-
Machine Learning Enhanced Power Converter Design and Prognostic Health Monitoring in DC Distribution Systems
… Graph Variational Autoencoders and fine-tuned GPT-2 models to generate novel, high-performance converter designs. Chapter 4 addresses the difficulty of scalable, real-time grid health assessment by proposing an FPGA-accelerated, impedance-based monitoring method using neural network regression …