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 6 of 6 for “"Learning--Graphic methods"”.
-
The effect of graphic organizers on the academic achievement of fourth grade students
… of this study was to determine the effect that graphic organizers have on the academic achievement of fourth grade students. The sample was a fourth grade classroom in an elementary school in southern New Jersey. The researcher taught the students two different social studies chapters. The …
-
Modeling Data Metrics And Distributions For Representation And Efficient Transfer Learning
Representation Learning and Transfer Learning are fundamental challenges in deep learning, particularly for downstream computer vision tasks. While existing research predominantly focuses on loss functions and network architectures, this dissertation explores how modeling distance metrics and data …
-
Graph Neural Networks for Improved Interpretability and Efficiency
… supplementary input features of nodes. Machine learning algorithms or traditional network science tools have limitation in their capability to make use of both network topology and node features. Graph Neural Networks (GNNs) provide an efficient framework combining both sources of information to …
-
In Pursuit of Low-dimensional Manifold Structures in High-dimensional Data
… such structures also contributes to improved learning and inference performance. A majority of existing work assume linear data models which fail to effectively capture the complex patterns of real-world problems. Non-linear models on the other hand typically hinge upon local neighborhood …
-
Advancing Anomaly Detection with Robust and Graph-Based Learning Methods: From Support Vector Data Description to Graph Neural Networks.
… explores robust and scalable anomaly detection methods, focusing on enhancing support vector techniques to accommodate complex data structures like graphs. The first study introduces the Robust Support Vector Data Description (RSVDD) model, which improves standard SVDD by incorporating a …
-
High-Performance Computational Kernels for Algorithm-System Co-Design in Machine Learning: Enabling Efficient GCN Training and LLM Inference Serving.
The rapid advancement of machine learning, from Graph Convolutional Networks (GCNs) to transformer-based Large Language Models (LLMs), continues to expose fundamental limitations in memory efficiency, scalability, and system reliability. GCNs are critical for domains such as biomedical modeling, …