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 13 of 13 for “"AI for Science"”.
-
Towards Efficient AI for Science in Scalable and High Performance Distributed System
Artificial intelligence (AI) has seen rapid development over the last few decades, significantly impacting various domains such as computer vision and natural language processing. In recent years, machine learning methods have been increasingly applied to the scientific discovery process, …
-
Rethinking local structural awareness in graph representation learning
… to social networks and relational databases. For these types of problems, graph representation learning has emerged as a powerful framework for reasoning. Models such as graph neural networks (GNNs) are particularly appealing due to their ability to capture complex, implicit relationships. …
-
Geometric Deep Learning for Molecular Discoveries
… rapid advancement of artificial intelligence (AI), its applications in scientific research have grown significantly, giving rise to the research area of AI for science (AI4Science). In this dissertation, we focus on AI for molecular science, such as small molecules and proteins, aiming to build …
-
Design and Evaluation of Autonomous Language Agents in Scientific Discovery and Clinical Reasoning
This dissertation establishes a framework for the design, implementation, and evaluation of autonomous and collaborative Large Language Model (LLM) agents within scientific discovery and clinical reasoning workflows. It first presents Agent Laboratory, a multi-agent system utilizing mle-solver and …
-
Machine Learning, Artificial Intelligence and High-throughput Experimentation for Material Discovery of Hybrid Organic Inorganic Perovskites
… artificial intelligence–driven framework for accelerated discovery and optimization of hybrid organic–inorganic perovskites through the integration of automated experimentation, probabilistic modeling, and autonomous decision making. The central objective is to transform conventional …
-
Solving Forward and Inverse Problems for Seismic Imaging using Invertible Neural Networks
Full Waveform Inversion (FWI) is a widely used optimization technique for subsurface imaging where the goal is to estimate the seismic wave velocity beneath the Earth's surface from the observed seismic data at the surface. The problem is primarily governed by the wave equation, which is a …
-
Multivariate Time-Series Deep Learning for Short-Term Forecasting of Lost Circulation in Drilling Operations
… interactions among drilling parameters, formation conditions, and operational states. This thesis investigates the use of multivariate time-series deep learning models for short-term lost circulation prediction based on real field drilling data. The dataset used in this study was …
-
IMPLICIT NEURAL CONFIGURATION INTERACTION
… that combines the two orthogonal approaches for capturing correlation, namely Configuration Interaction (CI) and Generalized Slater Determinant (GSD), where both the coefficients and the basis are variational and are capable of capturing correlation, thus connecting the two distinct …
-
Generative Bayesian Optimization for Structured Design
Black-box optimization is a general framework for problems where our goal is to find an input that maximizes some real-valued objective function. Typically, no mathematical form is available for this objective function, and it may be expensive to evaluate, making it a black-box. Many practical …
-
Interpretable machine learning and governing law discovery
… data, but prediction alone is not sufficient for scientific discovery. In many real-world systems, the goal is not only to approximate observations, but to recover interpretable coordinates, identify governing equations, quantify uncertainty, and make reliable predictions from sparse, noisy, …
-
Human-in-the-loop Machine Learning System via Model Interpretability
… experience can be challenging. My thesis aims to address the major challenges in interpretable machine learning and lay the foundations for a more interactive machine learning system.</p><p>In this thesis, I first tackle the challenge of building machine learning models with …
-
Structured Explanations for Scientific Domains Building on Foundation Models
… functions as a black box. In high-stakes domains such as science and medicine, earning expert trust, and thereby enabling adoption, requires structured explanations that expose both the units of reasoning and the reasoning process itself to those experts. At the same time, experts should be …
-
Leveraging Large Language Models for Nanomaterials Discovery and Synthesis
… with desired properties are crucial for addressing global energy, healthcare, and environmental sustainability challenges. Traditional trial-and-error approaches to materials synthesis optimization are time-consuming and resource-intensive. This thesis begin with exploring applying …