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 147 for “"Machine Learning Optimization"”.
-
A Dynamical Systems Perspective on Machine Learning Optimization
The rapid advancement of machine learning has been enabled in large part by effective optimization algorithms for training increasingly complex models. Given the central role of optimization in machine learning, developing deeper understanding of these algorithms is essential. Traditionally, …
-
Understanding Adaptivity in Machine Learning Optimization: Theories and Algorithms
Optimization plays an indispensable role in modern machine learning, due to its necessity in many aspects, especially in model training. Over the past decade, the rapid development of research in deep machine learning models posed many new challenges for machine learning optimization. As a result, …
-
Machine Learning, Optimization, and Anti-Training with Sacrificial Data
Traditionally the machine learning community has viewed the No Free Lunch (NFL) theorems for search and optimization as a limitation. I review, analyze, and unify the NFL theorem with the many frameworks to arrive at necessary conditions for improving black-box optimization, model selection, and …
-
Applications of diffusion processes: machine learning, optimization, and sampling
Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2024-08-01
-
Development of fractured reservoir uncertainty calibration models based on machine learning optimization
… that make accurate modeling, calibration, and optimization highly challenging. This dissertation presents a comprehensive framework for the development of fractured-reservoir uncertainty-calibration models based on machine-learning optimization, field monitor data, and GPU-accelerated numerical …
-
SEM Image Reduction and Analysis for Machine Learning Optimization of Metal Halide Perovskites
… labs is creating a multi-scale statistical machine learning (ML) model to optimize the entire process from perovskite synthesis to device performance. The collaboration is called SPIRALs, which stands for Science and Processing Informed by Rational Algorithmic Learning (SPIRALs). A key …
-
Experimental characterization and machine learning optimization of polymer nanocomposite membranes for carbon capture systems
… this research developed and applied three machine learning (ML) techniques, Deep Neural Networks (DNN), Random Forest (RF), and XGBoost models, to analyze the CO2 permeability and CO2/N2 selectivity of nanocomposite membranes. The datasets for CO2/N2 separation were sourced from our …
-
Gaussian Process Regression applied to Marine Energy Turbulent Source Tuning via Metamodel Machine Learning Optimization
… Surrogate models have garnered interest as optimization tools because they maximize the utility of expensive information by building predictive models in place of computational or experimentally expensive model runs. Marine hydrokinetic current energy converters require large-domain …
-
Enhancing Mechanical Properties and Design of Metallic Glasses Through Nanoscale Heterogeneities and Machine Learning Optimization
… simulations. This dissertation integrates machine learning with multiscale and multiphysics models to uncover the mechanisms that explain the emergence of mechanical behaviors of MGs and explores a massive design space for property optimization. These findings provide valuable insights into …
-
Steering Center Control: A Road Lane Centering Control System for Self-Driving Vehicles
… Neural Network, Model Predictive Control, Machine Learning Optimization, Full-Sate Feed-forward with Feedback Control, EPS steering systems, Lane Centering Control
-
Learning with Less: Low-rank Dynamics, Communication, and Introspection in Machine Learning
… empirical and theoretical analysis of the optimization methods in machine learning, and the underlying role that the matrix rank of utilized learning statistics plays in these algorithms. We show that this new perspective on machine learning optimization provides benefits in terms of …
-
Discovering Discrete Structures using SDP Relaxation: Hidden Integrality, Statistical Optimality and Semirandom Robustness
… and ongoing effort in the communities of machine learning, optimization and statistics. We will introduce the problem under a wide range of generative models, including the well-known Stochastic Block Model and Gaussian Mixture Model. After discussing several popular algorithms, we will …
-
Data-Driven Constrained Control
… system identification. This effort leverages machine learning, optimization, and control theory to bridge theoretical rigor and practical applicability. Deterministic guarantees are provided based on the Lipschitz continuity of the system, and probabilistic guarantees through scenario …
-
Analysis of dry spot formation in RTM through optimization of non-Newtonian resin parameters
… how they affect void formation. Finally, we use Machine Learning Optimization tools to determine the best set of resin rheology parameters from the conceivable sample space, and study the corresponding effects on fill. Through this innovative approach, we are able to establish a simulation …
-
Revealing structure in trained neural networks through dimensionality-based methods
Neural networks trained by machine learning optimization methods are currently being analyzed to shed light on brain function. While exciting progress is being made, the complicated nature of the network models typically considered has made ``opening the black box'' a significant challenge. In this …
-
Quantum Machine Learning for Recognizing Gaussian Discord
… the Gaussian quantum discord using quantum machine learning. We review in detail the CV quantum computing systems that implement hybrid quantum-classical machine learning algorithms. Both Gaussian and non-Gaussian transformations are necessary to construct universal quantum computing …
-
MACHINE LEARNING AND OPTIMIZATION FOR HEALTHCARE AND ENERGY SYSTEMS
… and storing data. In this dissertation, we used machine learning, optimization techniques, and data from healthcare and energy systems to build predictive models and discover new knowledge to guide decision-making and improve the efficiency and sustainability of these systems. We also used …
-
Using Neural Networks to Maximize a Submodular Function
It is accurate to say that optimization plays a huge role in the field of machine learning. Majority of the machine learning problems can be reduced to optimization problems and having the ability to solve such group of optimization problems be- comes the goal of all the people who are interested …
-
Learning and Control for Energy Systems under Uncertainty
… we leverage tools that interface between machine learning, optimization, and control to address three types of uncertainties: environmental uncertainty, model uncertainty, and uncertainty from users' interactions. The first part of the dissertation considers energy system control under …
-
Parametrically Homogenized Crystal Plasticity Model for Nickel-based Superalloys: Intragranular Microstructures To Polycrystalline Aggregates
… of computational tools from statistics, machine learning, optimization, and continuum mechanics. A multiscale modeling pipeline is established in the development of a parametrically-homogenized crystal plasticity model (PHCPM). The PHCPM explicitly incorporates morphological statistics of …
Page 1 of 8