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 31 for “"Training data generation"”.

  1. Controlled training data generation with diffusion models

    … a text-to-image generative model to produce training data specifically “useful” for supervised learning. Unlike previous works that employ an open-loop approach and pre-define prompts to generate new data using either a language model or human expertise, we develop an automated closed-loop …

    texas Repository record for Controlled training data generation with diffusion models (opens in a new tab)

  2. A Tale of Two Basins: Attributing 40 Years of Wetland Change in the Lake Erie and Lake Ontario Sub-Basins While Exploring the Potential of Large Language Models for Training Data Generation in Remote Sensing

    … in remote sensing: generating sufficient training and validation data. To confront this, this thesis first benchmarks eight large language models (LLMs) for land cover classification, finding they perform well on spectrally distinct classes but struggle with complex ones, making them …

    guelph Repository record for A Tale of Two Basins: Attributing 40 Years of Wetland Change in the Lake Erie and Lake Ontario Sub-Basins While Exploring the Potential of Large Language Models for Training Data Generation in Remote Sensing (opens in a new tab)

  3. INTELLIGENT FAULT DIAGNOSIS WITH DOMAIN ADAPTATION FOR QUADROTOR UAVS

    In this thesis, the author proposes a data-driven approach based on deep learning to develop a propeller fault classifier for quadrotor UAVs, in which the challenges from data collection to the difference between the training environment and the real flight environment are addressed. Firstly, a …

    nus Repository record for INTELLIGENT FAULT DIAGNOSIS WITH DOMAIN ADAPTATION FOR QUADROTOR UAVS (opens in a new tab) Download file for INTELLIGENT FAULT DIAGNOSIS WITH DOMAIN ADAPTATION FOR QUADROTOR UAVS (opens in a new tab)

  4. Development of urban area geospatial information products from high resolution satellite imagery using advanced image analysis techniques

    The latest generation of commercial satellite imaging sensors have a number of characteristics (e.g. high spatial resolution, multispectral bands, and quick revisit time), that make them ideal data sources for a variety of urban area applications. The goal of this doctoral research was to develop …

    missouri Repository record for Development of urban area geospatial information products from high resolution satellite imagery using advanced image analysis techniques (opens in a new tab)

  5. Characterization of Shape Memory Alloys Using Artificial Neural Networks

    … procedures necessitate extensive data collection and data processing, creating a high barrier of entry for shape memory alloy application. This thesis develops a novel approach in which a form of computational intelligence is applied to the task of shape memory alloy material …

    tamu Repository record for Characterization of Shape Memory Alloys Using Artificial Neural Networks (opens in a new tab)

  6. Structure-Guided Approaches for Robust Language Model Reasoning

    … approaches—such as collecting human-generated data—cannot reliably predict model failure modes, distinguish genuine reasoning from complex memorization patterns, nor guarantee synthetic data quality.This thesis explores the idea that imbuing tasks with explicit structure provides the control …

    washington Repository record for Structure-Guided Approaches for Robust Language Model Reasoning (opens in a new tab)

  7. Deep learning for field-based automated high-throughput plant phenotyping

    … different backbones to process the raw image data collected by autonomous ground-robotic platforms. The proposed high-throughput phenotyping framework also involves tracking algorithms for robust decision-making using multiple image frames from the video data collected by the robots. In the …

    iastate Repository record for Deep learning for field-based automated high-throughput plant phenotyping (opens in a new tab)

  8. Accelerated CO2 Storage Optimization Using Multi-Resolution Fourier Neural Operator: Field Application at the Illinois Basin Decatur Project (IBDP)

    … optimization during CO2 sequestration. A data-driven proxy model is developed to accelerate the optimization workflow, which makes it scalable to large scale field applications. Our deep learning workflow utilizes a recently developed machine learning architecture, Fourier Neural Operator …

    tamu Repository record for Accelerated CO2 Storage Optimization Using Multi-Resolution Fourier Neural Operator: Field Application at the Illinois Basin Decatur Project (IBDP) (opens in a new tab) Embargoed until 2026-12-01

  9. Studies on the effects of wiring density on chip package interaction and design optimization with machine learning

    … a validated multi-scale finite element model for training data generation. An adaptive sampling scheme is developed to optimize the training process with a steepest descent algorithm. Multiple machine learning algorithms were evaluated for model development. A significant improvement on prediction …

    texas Repository record for Studies on the effects of wiring density on chip package interaction and design optimization with machine learning (opens in a new tab)

  10. Encoding of Digitised Documents

    … through practical applications related to training data generation/semi-automatic OCR and faithful reproduction using document specific alphabets and fonts.

    salford Repository record for Encoding of Digitised Documents (opens in a new tab)

  11. Deep learning based solutions to biomedical image analysis problems of the upper aerodigestive tract

    … studies produce an abundance of image and video data. Clinical practice often relies on subjective, qualitative interpretation of image and video data, whereas scientific studies often involve extremely labor intensive manual analysis methods creating a bottleneck in scientific discovery. …

    missouri Repository record for Deep learning based solutions to biomedical image analysis problems of the upper aerodigestive tract (opens in a new tab)

  12. Scalable learning for expanding robot vision

    … domain adaptation, image de-noising and finally training data generation. However, the boundaries between these categories are fluid, allowing for complementary operation. </p> <p>Throughout this work, we successfully demonstrate domain adaptation for localisation across any weather and …

    oxford Repository record for Scalable learning for expanding robot vision (opens in a new tab)

  13. Towards cognitive manufacturing: Integrating ontologies, digital twins, and large language models for industrial systems

    … industrial domains into highly interconnected, data-driven, and intelligent ecosystems. While these advancements offer unprecedented opportunities for operational optimization and informed decision-making, they also pose enduring challenges, including the unification of heterogeneous data, …

    aalto Repository record for Towards cognitive manufacturing: Integrating ontologies, digital twins, and large language models for industrial systems (opens in a new tab)

  14. Language Models: Generator and Labeler

    … models have been trained on massive amounts of data using advanced learning algorithms, enabling them to perform a wide range of Natural Language Processing (NLP) tasks with great accuracy. This has made them highly reliable and robust, with state-of-the-art or comparable performance on various …

    gatech Repository record for Language Models: Generator and Labeler (opens in a new tab)

  15. Stochastic Reduced-Order Representations for Parametric and Model-Form Uncertainties, with Applications to Fracture and Molecular Dynamics Simulations

    … Hamiltonian Monte Carlo sampling, used for data augmentation. Focusing on phase-field simulations of brittle fracture in random mesostructures, the approach is compared with state-of-the-art methods, including the Fourier Neural Operators and PCA-Net. The framework is shown to achieve …

    duke Repository record for Stochastic Reduced-Order Representations for Parametric and Model-Form Uncertainties, with Applications to Fracture and Molecular Dynamics Simulations (opens in a new tab)

  16. Application of Reduced Order Models for Field-Scale Simulation and Optimization of Unconventional Reservoir and Carbon Storage Projects

    … matching, CO2 injection optimization, and training data generation for machine learning models. This issue becomes more severe when dealing with complex reservoir systems, such as unconventional formations with hydraulic fractures and CCS formations with complex fluid components. The need …

    tamu Repository record for Application of Reduced Order Models for Field-Scale Simulation and Optimization of Unconventional Reservoir and Carbon Storage Projects (opens in a new tab) Embargoed until 2027-08-01

  17. Application of Reduced Order Models for Field-Scale Simulation and Optimization of Unconventional Reservoir and Carbon Storage Projects

    … matching, CO2 injection optimization, and training data generation for machine learning models. This issue becomes more severe when dealing with complex reservoir systems, such as unconventional formations with hydraulic fractures and CCS formations with complex fluid components. The need …

    tamu Repository record for Application of Reduced Order Models for Field-Scale Simulation and Optimization of Unconventional Reservoir and Carbon Storage Projects (opens in a new tab) Embargoed until 2027-08-01

  18. Application of Reduced Order Models for Field-Scale Simulation and Optimization of Unconventional Reservoir and Carbon Storage Projects

    … matching, CO2 injection optimization, and training data generation for machine learning models. This issue becomes more severe when dealing with complex reservoir systems, such as unconventional formations with hydraulic fractures and CCS formations with complex fluid components. The need …

    tamu Repository record for Application of Reduced Order Models for Field-Scale Simulation and Optimization of Unconventional Reservoir and Carbon Storage Projects (opens in a new tab) Embargoed until 2027-08-01

  19. Application of Reduced Order Models for Field-Scale Simulation and Optimization of Unconventional Reservoir and Carbon Storage Projects

    … matching, CO2 injection optimization, and training data generation for machine learning models. This issue becomes more severe when dealing with complex reservoir systems, such as unconventional formations with hydraulic fractures and CCS formations with complex fluid components. The need …

    tamu Repository record for Application of Reduced Order Models for Field-Scale Simulation and Optimization of Unconventional Reservoir and Carbon Storage Projects (opens in a new tab) Embargoed until 2027-08-01

  20. Application of Reduced Order Models for Field-Scale Simulation and Optimization of Unconventional Reservoir and Carbon Storage Projects

    … matching, CO2 injection optimization, and training data generation for machine learning models. This issue becomes more severe when dealing with complex reservoir systems, such as unconventional formations with hydraulic fractures and CCS formations with complex fluid components. The need …

    tamu Repository record for Application of Reduced Order Models for Field-Scale Simulation and Optimization of Unconventional Reservoir and Carbon Storage Projects (opens in a new tab) Embargoed until 2027-08-01

Page 1 of 2