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 53 for “"Hyper parameter tuning"”.

  1. Hyper-parameter Tuning for Search-based Test Case Generation

    … search methods is highly dependent on their hyper-parameters, there is a need to study hyper-parameter tuning in this domain. In this study, we first studied the effectiveness of hyper-parameter tuning for search-based test generation exhaustively analyze 1,200 hyper-parameter configurations …

    calgary Repository record for Hyper-parameter Tuning for Search-based Test Case Generation (opens in a new tab)

  2. AutoRec: An Automated Recommender System

    … at the expense of model adaptability and model tuning complexity. As shown in Figure 1, the originally apt model often either becomes obsolete or requires hyper-parameter tuning as the recommendation task at hand changes and additional types and amounts of data are collected over time. The …

    tamu Repository record for AutoRec: An Automated Recommender System (opens in a new tab)

  3. Algorithms based on Deep Learning in the context of Agriculture 4.0

    … of these studies through hybrid approaches and hyper-parameter tuning techniques. Three distinct case studies were conducted: (i) automated identification of olive cultivars; (ii) detection and monitoring of pests; and (iii) classification of fruit ripeness. These studies involved the …

    minho-thes Repository record for Algorithms based on Deep Learning in the context of Agriculture 4.0 (opens in a new tab) Embargoed until 2027-03-26

  4. Transfer Learning, Model Interpretation, and Dataset Bias Analysis for Automated Violence Detection from Video

    … video footage. This system is developed by fine-tuning a convolutional neural network that has previously demonstrated success on general action recognition tasks. This thesis explores two new techniques to improve the accuracy of the fine-tuned model. The first is a data augmentation technique …

    marquette Repository record for Transfer Learning, Model Interpretation, and Dataset Bias Analysis for Automated Violence Detection from Video (opens in a new tab)

  5. Online experiment design with causal structures

    … computational advertising systems, online parameter tuning services are inherently online; i.e. these systems need to continually collect data, take decisions to optimize a certain objective and then collect more data with the objective of improving their predictive abilities. This leads to …

    texas Repository record for Online experiment design with causal structures (opens in a new tab)

  6. Data-Driven Methods for Virtual Energy Storage System Optimisation Under Uncertainties

    … suffer from computational inefficiency for hyper-parameter tuning, and security issues for constraint violations. In chapter 2, a novel hierarchically coordinated control methodology is proposed which fully addresses the mutual impact between local and central controllers. In chapter 3, a …

    unsw Repository record for Data-Driven Methods for Virtual Energy Storage System Optimisation Under Uncertainties (opens in a new tab)

  7. FORWARD BACKWARD SPLITTING UNROLLING STRATEGIES FOR INVERSE PROBLEMS RESOLUTION

    … algorithm performance depends largely on hyper-parameters (e.g. regularization parameters, gradient descent step...) thus hyper-parameter tuning for inverse problem resolution is an essential task allowing to compute high quality solution with reasonable computing time. A way to handle …

    nus Repository record for FORWARD BACKWARD SPLITTING UNROLLING STRATEGIES FOR INVERSE PROBLEMS RESOLUTION (opens in a new tab) Download file for FORWARD BACKWARD SPLITTING UNROLLING STRATEGIES FOR INVERSE PROBLEMS RESOLUTION (opens in a new tab)

  8. Online cross-project prediction of defect-inducing software changes

    … machine learning models are also sensitive to hyper-parameter choice and may underperform if hyperparameters are not configured properly. Tuning methods used for offline learning are not suitable for online learning because in online learning, the best hyper-parameter choice may change over …

    birmingham Download PDF for Online cross-project prediction of defect-inducing software changes (opens in a new tab)

  9. On Cyber Attack Detection: Evaluating Different Datasets Using K-Nearest Neighbor Machine Learning Algorithm

    … Component Analysis (PCA), data balancing and hyper-parameter tuning to help improve the outcome of KNN prediction. These tools allow us to identify the key features in each dataset and increase the accuracy and precision of the machine learning algorithm to identify anomalous data packets. Our …

    tamu Repository record for On Cyber Attack Detection: Evaluating Different Datasets Using K-Nearest Neighbor Machine Learning Algorithm (opens in a new tab)

  10. A Transfer Learning Approach for Automatic Mapping of Retrogressive Thaw Slumps (RTSs) in the Western Canadian Arctic

    … and backbone trainable layers, and performed hyper-parameter tuning and determined the optimal learning rate, momentum, and decay rate for each of the model settings. Our final model successfully mapped most of the RTSs in our test sites, with F1 scores ranging from 0.61 to 0.79. Our study …

    ottawa-retro Repository record for A Transfer Learning Approach for Automatic Mapping of Retrogressive Thaw Slumps (RTSs) in the Western Canadian Arctic (opens in a new tab)

  11. ENHANCING ACCIDENT INVESTIGATION USING TRAFFIC CCTV FOOTAGE

    … on imbalanced datasets? (Q2) How will the hyper parameter tuning affect the model performance? (Q3) How effective is the proposed model compared to existing work? The findings are: Q1. The effectiveness of our model depends on the implementation of augmentation techniques that pay attention …

    csusb Repository record for ENHANCING ACCIDENT INVESTIGATION USING TRAFFIC CCTV FOOTAGE (opens in a new tab)

  12. Machine-assisted translation by Human-in-the-loop Crowdsourcing for Bambara

    … data discovery, data preparation, model hyper-parameter tuning, the development of a crowdsourcing platform for humans in the loop, vocabulary sizing, and segmentation. We present a novel approach to machine translation (MT) for under-resourced languages by improving the quality of the …

    rit Repository record for Machine-assisted translation by Human-in-the-loop Crowdsourcing for Bambara (opens in a new tab)

  13. FORECASTING THE DAILY PERCENTAGE OF DELAYED FLIGHTS BASED ON THE NATIONAL WEATHER DATA

    … random forest model by training and rigorously hyper-parameter tuning. We measured the assessment of the fitted model with the evaluation metrics, such as mean absolute error, root mean squared error, and coefficient of determination scores. The random forest model with the evaluation scores of …

    montana Repository record for FORECASTING THE DAILY PERCENTAGE OF DELAYED FLIGHTS BASED ON THE NATIONAL WEATHER DATA (opens in a new tab)

  14. FORECASTING THE DAILY PERCENTAGE OF DELAYED FLIGHTS BASED ON THE NATIONAL WEATHER DATA

    … random forest model by training and rigorously hyper-parameter tuning. We measured the assessment of the fitted model with the evaluation metrics, such as mean absolute error, root mean squared error, and coefficient of determination scores. The random forest model with the evaluation scores of …

    montana-tech Repository record for FORECASTING THE DAILY PERCENTAGE OF DELAYED FLIGHTS BASED ON THE NATIONAL WEATHER DATA (opens in a new tab)

  15. Bias and Fairness of Evasion Attacks in Image Perturbation

    … stands, the Fawkes system has a fixed set of hyper parameters for amount of perturbations added per image, which essentially means that they consider all users be treated identically in terms of amount of perturbations added. However, from testing our hypothesis through running various …

    central-wash Repository record for Bias and Fairness of Evasion Attacks in Image Perturbation (opens in a new tab)

  16. Automatizuotas retas modelių identifikavimas ir parametrų optimizavimas reakcijos-difuzijos sistemoms /

    … of Non-linear Dynamics} (SINDy), exhaustive hyper-parameter sweeps, and a two-stage \emph{term-stability pruning} strategy that removes rarely selected or chronically over-fitting features before Pareto-optimal model selection. The framework is benchmarked on four canonical one-dimensional …

    vilnius Repository record for Automatizuotas retas modelių identifikavimas ir parametrų optimizavimas reakcijos-difuzijos sistemoms / (opens in a new tab)

  17. Multi-label classification using conformal prediction

    … that any multiple testing procedure wrapped with hyper-parameter tuning produces an adaptive version, which overcomes the conservativeness of the fixed-alpha method. Experiments have been conducted on synthetic data and real-life data sets and the results have been reported. Finally, Chapter 4 …

    njit Repository record for Multi-label classification using conformal prediction (opens in a new tab)

  18. Toward Data-centric Automated Machine Learning

    … solution: data preparation, model selection, hyper-parameter tuning, and deployment for feedback collection. While automated machine learning (AutoML) has been proposed to streamline the middle two processes and deliver efficient solutions without requiring laborious trial-and-error efforts, …

    rice Repository record for Toward Data-centric Automated Machine Learning (opens in a new tab)

  19. Machine Learning Model Selection for Predicting Properties of High Refractive Index Polymers

    … the primary focus. The traditional approach for hyper-parameter optimization of a given machine learning model is discussed in the beginning, followed by the need for more specialized techniques due to the shortcomings of this approach that are readily identified. We analyze two algorithms for …

    buffalo Repository record for Machine Learning Model Selection for Predicting Properties of High Refractive Index Polymers (opens in a new tab)

  20. Machine-Learning Based Optimization for Double-Layer Planar Spiral Coil Design in High-Frequency Wireless Power Transfer Systems

    … initialization, K-fold cross-validation, and hyper-parameter tuning, are adopted to improve the model performance, represented for Q-factor prediction accuracy. Then, optimizing the coil design is approached to explore the optimal design geometric parameters with the high Q. This is done using …

    washington Repository record for Machine-Learning Based Optimization for Double-Layer Planar Spiral Coil Design in High-Frequency Wireless Power Transfer Systems (opens in a new tab)

Page 1 of 3