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 35 for “"Pre-trained models"”.
-
Contextual topics: advancing text segmentation through pre-trained models and contextual keywords
… in creating structured, searchable text-based representations after digitizing paper-based documents. Traditionally, TS has been approached with sub-optimal feature engineering efforts and heuristic modelling. In this work, we explore novel supervised training procedures with a labeled text …
-
Grammatical analysis of Maltese text
… A neural approach is used to train a series of models that are able to take a Maltese word as input and produce its grammatical analysis as output. The data-set for this model was adapted from UniMorph, a universal morphological annotation project. The research focuses on creating and comparing …
-
Profile Modeling in Hierarchical Deep Architecture by Mutual Support
… Neural Networks (MFCNN), which can comprehensively implement face analysis including age, gender, race and emotion. Moreover, we take the advantages of the mutual support among different facial features from individual tasks to improve the performance of our model. We also contribute …
-
KB4DL: Building a Knowledge Base for Deep Learning
… we suffer from the lack of ability in interpretation and annotation of the outcomes from extensive and exhausting learning efforts. In this thesis, we propose an automatic metadata extraction both from DL models as well as their publications and populate ontologies in Deep Learning. The …
-
Utilizing network features to detect erroneous inputs
… misclassified, and adversarial examples. Previously, separate solutions have been proposed for each of these faulty data types; however, in this work I show that the collective set of erroneous inputs can be jointly identified with a single model. Specifically, I train a linear SVM …
-
Self-adaptation of software services based on user profile
… personality traits of users. For this purpose, pre-trained models focused on real-time emotion detection were used together with the BFI-2-S questionnaire to assess personality profiles. The experiment was conducted with 30 participants on the Neo Digital Skills platform, assessed using the User …
-
Evaluating Data Augmentation with Attention Masks for Context Aware Transformations
Transfer learning from large, pre-trained models and data augmentation are arguably the two most widespread solutions to the problem of data scarcity. However, both methods suffer from limitations that prevent more optimal solutions to natural language processing tasks. We consider that transfer …
-
Definition modelling for English and Portuguese: a comparison between models and settings
… but it is crucial for translation and interpreting. Definition Modelling (DM) is a task concerned with automatically generating definitions from embeddings. While most approaches to DM covers only English, this project aims at generating definitions for both Portuguese and English. DM is …
-
A Computational Framework for Learning from Complex Data: Formulations, Algorithms, and Applications
… For example, in computational biology, the expression data matrices are evolving, since gene expression controls are deployed sequentially during development in many biological processes. Investigations into the spatial and temporal gene expression dynamics are essential for understanding the …
-
Self-supervised Learning of Monocular Depth from Video
… challenges and contributions include: (i) Previous methods predict inconsistent depths over a video, which limits their uses in visual localization and mapping. To this end, I propose a geometry consistency loss that penalizes the multi-view depth misalignment in training, which enables …
-
Designing Macromolecules using Machine Learning and Simulations
… to macromolecules. The challenges around representing, comparing and learning over macromolecules are manifold. Current representations provide limited coverage of chemical space, and require significant customization to include non-natural monomers and non-linear topologies. Similarity …
-
MEng Thesis: Incorporating Structured Commonsense into Language Models
… (NLP). One such application is fine-tuning large pre-trained models to a wide variety of tasks. In this work, we propose methods to enhance these large language models by infusing them with information found in commonsense knowledge bases. Commonsense is basic knowledge about the world that humans …
-
Natural Language Processing for Behavior Change and Health Improvement
… in generating impactful cues. We use language models and fine-tune pre-trained models to classify EFT cue texts, facilitating further analysis of their features. Additionally, we leverage instruction-tuned Large Language Models (LLMs) to classify cue texts to address annotation variability. We …
-
A Study on Neural-based Code Summarization in Low-resource Settings
… with deep learning techniques has been comprehensively explored because of breakthroughs in code representation learning. Many code intelligence approaches have been proposed for the downstream tasks of this field in the past years, contributing to significant performance progress. Among …
-
Domain Playground: Extending Deep Learning Models to Open Domain Boundaries
Deep learning models have demonstrated monumental performance in classification tasks but require extensive data and training procedures to converge. Additionally, the performance is only guaranteed when there is no domain gap (e.g., the distribution of the source and target data are similar). …
-
Unmasking the imposters: towards improving the generalisation of deep learning methods for face presentation attack detection.
… employed in security applications. The most prevalent are presentation attacks. By using a photo, video, or mask of an authorized user, attackers can bypass face recognition systems. Fake presentation attacks are detected by the camera sensors of face recognition systems using face …
-
Improving Access to ETD Elements Through Chapter Categorization and Summarization
… academic vocabulary. We use large language models (LLMs) and fine-tune pre-trained models for these downstream tasks. We also develop a method to connect the ETD discipline and the department information to an ETD-centric classification system. To help guide the summarization model to create …
-
Transformer-based models for answer extraction in text-based question/answering
The success of transformer-based language models has led to a surge of research in various natural language processing tasks, among which extractive question-answering/answer span detection, has received considerable attention in recent years. However, to date, no comprehensive studies have been …
-
Improving Text Classification Using Graph-based Methods
… been investigated for the task. Sequence- based models can successfully capture semantics in local consecutive text sequences. On the other hand, graph-based models can preserve global co-occurrences that capture non- consecutive and long-distance semantics. A text representation approach that …
-
Exploration and Comparison of Image-Based Techniques for Strawberry Detection
… the unripe strawberry, this thesis first trained the Support Vector Machine classifier based on the HOG feature. After optimizing the classifier through hard negative mining, the truth-positive rate reached 81.11%.</p> <p>Finally, when exploring the deep learning model, two detectors based …
Page 1 of 2