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 4 of 4 for “"Mislabeled Examples"”.

  1. Comparing Methods for Automatic Identification of Mislabeled Data

    … thesis compares three methods for identifying mislabeled examples in datasets: Dataset Cartography (Swayamdipta et al. [2020]), Cleanlab, (Northcutt et al. [2021b]), and Ensem- bling (Brodley and Friedl [1999], Reiss et al. [2020]). Mislabeled examples in the training data of a dataset …

    washington Repository record for Comparing Methods for Automatic Identification of Mislabeled Data (opens in a new tab)

  2. Label Noise Cleaning Using Support Vector Machines

    Mislabeled examples affect the performance of supervised learning algorithms. Two novel approaches to this problem are presented in this Thesis. Both methods build on the hypothesis that the large margin and the soft margin principles of support vector machines provide the characteristics to select …

    usf Repository record for Label Noise Cleaning Using Support Vector Machines (opens in a new tab)

  3. Efficient online uncertainty management : Conformal-in-the-Loop for measuring and actioning uncertainty at training time

    … is often used for online labeling and pruning mislabeled examples. However, these methods are usually computationally expensive and require multiple stages or training runs. The final chapter applies conformal prediction for efficient online data curation in a single training run. It proposes a …

    ubc Repository record for Efficient online uncertainty management : Conformal-in-the-Loop for measuring and actioning uncertainty at training time (opens in a new tab) Download PDF for Efficient online uncertainty management : Conformal-in-the-Loop for measuring and actioning uncertainty at training time (opens in a new tab)

  4. Active Cleaning of Label Noise Using Support Vector Machines

    … small, but important class needs to have all its examples identified. Typical solutions to the label noise problem involve creating classifiers that are robust or tolerant to errors in the labels, or removing the suspected examples using machine learning algorithms. Finding the label noise …

    usf Repository record for Active Cleaning of Label Noise Using Support Vector Machines (opens in a new tab)