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 20 for “"gradient-free"”.
-
Global Optimization Techniques Based on Swarm-intelligent and Gradient-free Algorithms
… its saving in the computational power with the gradient-free attribute, are two solutions that deserve attention. Many researchers have exploited their merits in widely challenging applications. However, there is a known fact that both of them suffer from a severe drawback, non- effectively …
-
Optimization of an industrial centrifugal blower using gradient-free and gradient-based (adjoint) approaches
… Bien que les méthodes d’optimisation sans gradient soient couramment utilisées pour optimiser la forme aérodynamique des turbomachines, leur coût de calcul reste généralement élevé, notamment lorsqu’un grand nombre de variables de conception est impliqué. En revanche, la méthode adjointe, …
-
Optimizing the Design of Robot Environments via Interleaved Optimization and White-Box Motion-Planning
… these motion planning algorithms into gradient-free optimization loops that operate over the design space of the robot’s environment. These algorithms are, unfortunately, compute-hungry and thus will dominate the runtime of the optimization process. This motivates our second key …
-
Multidelity methods for multidisciplinary system design
… calibration schemes can exploit high- fidelity gradient information if available, but when not, convergence is still demonstrated for a gradient-free calibration scheme. The gradient-free calibration is novel in that it enables rigorous optimization of high-fidelity simulations that are …
-
Proposing effective coordinate search methods for solving large-scale expensive black-box optimization problems
… Search (CS) algorithm are proposed. CS is a gradient-free technique and we have enhanced them for solving Black-box, non-convex, and expensive large-scale problems. These CS-based algorithms can handle mixed-type variables. When an optimization problem is large-scale and expensive, it is a …
-
Trustworthy Learning and Uncertainty Quantification under Constraints
… namely posthoc uncertainty learning; reliable gradient-free and likelihood-free prompt tuning; and trustworthy unsupervised multi-source-free domain adaptation.
-
A Method for Image Classification Using Low-Precision Analog Computing Arrays
… featuring simple threshold neurons. Appropriate, gradient-free, training algorithms, combining self-organization and supervised learning are developed and tested with two benchmark problems (MNIST hand-written digits and traffic signs). Software simulations evaluate the methods under various …
-
Discovering and Engineering the Computation Underlying Large Intelligent Agents
… to improve their empirical generalization in a gradient free manner, sometimes by as much as 30% points on language understanding benchmarks. Following that, I show how to decipher the structure of another (black box) language-like system, the naturally arising communication system of sperm …
-
Novel Approaches to Discovery and Optimization in Physics: Symbolic Regression, Bayesian Optimization, and Topological Photonics
… level-set parameterization and standard gradient-free optimization algorithms. My approach is able to discover novel 3D photonic crystals in several topology settings requiring no prior knowledge of topological candidates, thus indicating a path towards the automated discovery of novel …
-
SCALABLE MATCHING OF DEFORMED IMAGES
… distortion correction for echo-planar MRI, and gradient-free landmark-guided registration for lung CT scans.
-
Electrochemical Model Based Fault Diagnosis of Lithium Ion Battery
A gradient free function optimization technique, namely particle swarm optimization (PSO) algorithm, is utilized in parameter identification of the electrochemical model of a Lithium-Ion battery having a LiCoO2 chemistry. Battery electrochemical model parameters are subject to change under severe …
-
Multi-Fidelity Analysis and Optimization of Lightweight Structures Subject to Significant Fluid-Structure Interaction Effects
… repeated high-fidelity CFD analyses. Moreover, gradient-based optimization is difficult to apply due to the challenges of differentiating through coupled CFD-CSD solvers. These challenges are addressed in this dissertation by first leveraging gradient-free methods, such as genetic algorithms, to …
-
Novel optimizers for multi-objective deep learning
… (Adam) is one of the most commonly used gradient-based optimization strategies in the field of neural networks. Adam is a single-objective single-solution optimizer that emerges as the victor in the majority of competitions. However, committing to a single loss function often fails to …
-
Microfluidics and chemical kinetics to analyse protein interactions, aggregation, and physicochemical properties
… for the measurement of the protein pI, in a gradient-free manner. This approach overcomes a fundamental limitation of convectional techniques that is the achievement of a stable and well-controlled pH gradient. Secondly, I investigate the inhibiting effect of llama nanobodies on Aβ(1-42) …
-
Constrained multi-objective Bayesian optimization of simulated moving bed chromatography
… indexing time etc.) and hence, many degrees of freedom. To overcome the challenges of optimization, dynamic simulation is generally employed as a means of empirically estimating optimal operating conditions prior to experimentation, as a better alternative to trial-and-error approaches. However, …
-
ALUMINUM SCANDIUM NITRIDE (AlScN) FILMS FOR MICROELECTROMECHANICAL SYSTEMS (MEMS)
… Sc alloying levels, with controlled stress, and free of anomalous grains (AOGs) is demonstrated using reactive co-sputtering. The stress and AOG formation consider the Sc alloying range between 20.3 and 36.6 atomic % and for film thicknesses from 400 nm to 1000 nm. The combination of a gradient …
-
Optimisation of chaotic thermoacoustics
… the focus is on stability, sensitivity and gradient-based optimisation of the chaotic thermoacoustic system. First, we propose covariant Lyapunov vector analysis as a tool to calculate the stability of chaotic acoustics, making connections with eigenvalue and Floquet analyses. Second, …
-
Controlled particle systems for nonlinear filtering and global optimization
… the computational scalability of the solution. Gradient-free algorithms are attractive because in many practical situations, evaluating the gradient of the objective function may be computationally prohibitive. The thesis comprises two parts that are devoted to theory and applications, …
-
Data and Computation Efficient Meta-Learning
… to an unseen task as it does not involve gradient back propagation computations. We show that trained models are immediately deployable to continual learning and active learning where they can outperform existing approaches that do not leverage transfer learning. Finally, we investigate …
-
Synthesis and kinetic processes in designed polymers
… hydrogel film with imbedded radial chemical gradient to locally concentrate analytes in the local vicinity of SEIRA-active nanoantenna to improve the detection limit over that provided by SEIRA along. Using a positive charge gradient, embedded in a hydrogel film, a nerve agent simulant, …