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 “"multi objective bayesian optimization"”.

  1. Machine learning model selection with multi-objective Bayesian optimization and reinforcement learning

    … an expensive process, thus calling for efficient optimization algorithms. To tackle the challenge of distribution shift, novel resampling methods for the evaluation of robustness of neural network was proposed, as well as a domain generalization method using multi-objective bayesian optimization …

    lmu-germany Repository record for Machine learning model selection with multi-objective Bayesian optimization and reinforcement learning (opens in a new tab)

  2. Multi-objective Bayesian optimization of tokamak disruptions using fluid and kinetic models

    … is still an open question, and it represents a multi-objective optimization problem. We have used a Bayesian optimization framework to optimize the injected densities of deuterium and neon in a non-activated ITER-like tokamak set up. The cost function was constructed systematically to maximize …

    chalmers Repository record for Multi-objective Bayesian optimization of tokamak disruptions using fluid and kinetic models (opens in a new tab)

  3. MACHINE LEARNING DESIGN AND EXPERIMENTAL PRODUCTION OF RECYCLED ALUMINUM ALLOYS WITH MAGNESIUM AND IRON

    … This work applies machine learning with Multi-Objective Bayesian Optimization (MOBO) using Thermo-Calc simulations to design Al-Mg-Fe-Si-Cu-Zn alloys with improved castability and reduced porosity. The optimization targeted freezing range, shrinkage, drag coefficient, and microstructural …

    mtu Repository record for MACHINE LEARNING DESIGN AND EXPERIMENTAL PRODUCTION OF RECYCLED ALUMINUM ALLOYS WITH MAGNESIUM AND IRON (opens in a new tab)

  4. Physics-informed data-driven frameworks for materials discovery

    … thereby offering valuable insights for optimization and enhancement. In Chapter 3, physics-informed machine learning models are developed for the classification of printability and glass transition temperature (Tg) in additive manufacturing processes. By integrating fundamental …

    missouri Repository record for Physics-informed data-driven frameworks for materials discovery (opens in a new tab)

  5. Multiscale Modeling and Microstructure Design of Biodegradable Polymeric Scaffolds

    … of degradation and enable efficient design optimization. In this work, multi-scale modeling techniques are developed to design biodegradable polymeric scaffolds. A multi-objective Bayesian optimization approach is introduced to develop new molecular dynamics force fields for more accurate …

    gatech Repository record for Multiscale Modeling and Microstructure Design of Biodegradable Polymeric Scaffolds (opens in a new tab)

  6. Data Driven Structure-Property Relationships Towards Accelerating High-Throughput Alloy Discovery

    … the A&M BIRDSHOT center under data scarcity, a multi-objective Bayesian optimization framework is implemented to tune several overcomplete encoder-decoder neural networks to produce machine learning priors for the BIRDSHOT center's Bayesian Optimization framework. The models show strong …

    tamu Repository record for Data Driven Structure-Property Relationships Towards Accelerating High-Throughput Alloy Discovery (opens in a new tab) Embargoed until 2027-12-01

  7. Data Driven Structure-Property Relationships Towards Accelerating High-Throughput Alloy Discovery

    … the A&M BIRDSHOT center under data scarcity, a multi-objective Bayesian optimization framework is implemented to tune several overcomplete encoder-decoder neural networks to produce machine learning priors for the BIRDSHOT center's Bayesian Optimization framework. The models show strong …

    tamu Repository record for Data Driven Structure-Property Relationships Towards Accelerating High-Throughput Alloy Discovery (opens in a new tab) Embargoed until 2027-12-01

  8. Data Driven Structure-Property Relationships Towards Accelerating High-Throughput Alloy Discovery

    … the A&M BIRDSHOT center under data scarcity, a multi-objective Bayesian optimization framework is implemented to tune several overcomplete encoder-decoder neural networks to produce machine learning priors for the BIRDSHOT center's Bayesian Optimization framework. The models show strong …

    tamu Repository record for Data Driven Structure-Property Relationships Towards Accelerating High-Throughput Alloy Discovery (opens in a new tab) Embargoed until 2027-12-01

  9. Data Driven Structure-Property Relationships Towards Accelerating High-Throughput Alloy Discovery

    … the A&M BIRDSHOT center under data scarcity, a multi-objective Bayesian optimization framework is implemented to tune several overcomplete encoder-decoder neural networks to produce machine learning priors for the BIRDSHOT center's Bayesian Optimization framework. The models show strong …

    tamu Repository record for Data Driven Structure-Property Relationships Towards Accelerating High-Throughput Alloy Discovery (opens in a new tab) Embargoed until 2027-12-01

  10. Fused deposition modelling (FDM) 3D printing process optimization using a crowding-distance-augmented acquisition function

    … this thesis project aims at a budget-limited, bi-objective optimization problem that minimizes (i) wall-clock build time and (ii) an image-derived proxy of macro-scale surface artefacts, varraw, computed from photographs using a fixed, standardized image-processing protocol. A reproducible …

    calgary Repository record for Fused deposition modelling (FDM) 3D printing process optimization using a crowding-distance-augmented acquisition function (opens in a new tab)

  11. Variations on bayesian optimization applied to numerical flow simulations

    Bayesian Optimization (BO) has recently regained interest in optimization problems involving expensive black-box objective functions. Several variants have been proposed in the literature, such as including gradient and/or multi-fidelity information, and it has been extended to multi-objective …

    cadiz Repository record for Variations on bayesian optimization applied to numerical flow simulations (opens in a new tab)

  12. Machine Learning based Design and Optimization for High-Performance Semiconductor Packaging and Systems

    … and raise new challenges related to design optimization, design space exploration (DSE) and uncertainty quantification (UQ). Optimization of such systems correspond to finding the minimum or maximum of a high-dimensional, non-convex function in the black-box setting where the function …

    gatech Repository record for Machine Learning based Design and Optimization for High-Performance Semiconductor Packaging and Systems (opens in a new tab)

  13. Development of In-vitro Skin Models for Screening Bioactive Compounds and Modelling Diseases

    … properties of ECMs in various tissues. Through multi-objective Bayesian optimization, I identified hydrogel compositions with the elastic modulus and stress relaxation behavior mimicking the ECMs of healthy and scarred skin, as well as benign and malignant breast tumors. The ML algorithm also …

    toronto-retro Repository record for Development of In-vitro Skin Models for Screening Bioactive Compounds and Modelling Diseases (opens in a new tab)

  14. Ultrahigh Specific Strength and Energy Absorption of Additive Manufactured Nanoarchitected Carbon

    … which are thus far unattainable. First, we use multi-objective Bayesian optimization machine learning to design ultrahigh-performance non-intuitive beam element cross-sections which increase specific strength by as much as 75% as compared to uniform beam elements. Optimized nanolattices …

    toronto-retro Repository record for Ultrahigh Specific Strength and Energy Absorption of Additive Manufactured Nanoarchitected Carbon (opens in a new tab)

  15. Accelerating Manufacturing Decisions using Bayesian Optimization: An Optimization and Prediction Perspective

    … more complicated when there are conflicting objectives, sometimes with multiple goals. Furthermore, experiments are usually costly, time-consuming, and require expensive materials, man, and machine hours. So, each experiment is valuable and it's critical to determine the optimal experiment …

    wvu Repository record for Accelerating Manufacturing Decisions using Bayesian Optimization: An Optimization and Prediction Perspective (opens in a new tab)

  16. Part Performance Measurement, Analysis and Optimization for Binder Jetting Additive Manufacturing

    … tomography datasets were analyzed, where multiple global threshold techniques were evaluated to extract bulk density metrics. Through experimentally informed analysis, the threshold method Otsu, Mean and Isodata were the most consistent at segmenting computed tomography image of green …

    waterloo Repository record for Part Performance Measurement, Analysis and Optimization for Binder Jetting Additive Manufacturing (opens in a new tab)

  17. Investigation of Process-Structure Relationship for Additive Manufacturing with Multiphysics Simulation and Physics-Constrained Machine Learning

    … the P-S-P relationships for process design and optimization. First, there is a lack of fundamental understanding of the rapid solidification process during which microstructures are formed and the properties of solid parts are determined. Second, the curse of dimensionality in the process and …

    gatech Repository record for Investigation of Process-Structure Relationship for Additive Manufacturing with Multiphysics Simulation and Physics-Constrained Machine Learning (opens in a new tab)

  18. Machine Learning-Enabled Safety-Critical Model Predictive Control for Uncertain Dynamical Systems

    … focus on Reinforcement Learning (RL) and Bayesian Optimization (BO). We then leverage AI/ML to address several challenges in the control design and safe operation of uncertain dynamical systems. In many applications, ranging from autonomous vehicles and robotics to energy systems and …

    clemson Repository record for Machine Learning-Enabled Safety-Critical Model Predictive Control for Uncertain Dynamical Systems (opens in a new tab)

  19. Computational methods for automatic analog integrated circuit design

    … 1) The proposal of a family of black-box optimization algorithms, which take advantage of recent machine learning developments to accelerate and improve the exploration of the circuit’s design space, and 2) the development of a framework for procedural simulation execution and optimization …

    greece Repository record for Computational methods for automatic analog integrated circuit design (opens in a new tab)