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 103 for “"Label Noise"”.

  1. 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)

  2. Active Cleaning of Label Noise Using Support Vector Machines

    Large scale datasets collected using non-expert labelers are prone to labeling errors. Errors in the given labels or label noise affect the classifier performance, classifier complexity, class proportions, etc. It may be that a relatively small, but important class needs to have all its examples …

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

  3. Mitigating label noise in ECG data: A comparative analysis

    Label noise in electrocardiogram (ECG) datasets, where samples are incorrectly labelled, significantly hinders the performance of machine learning models by fitting to the incorrect labels. This type of noise can arise from several factors, such as human error, inter-expert variability, or obsolete …

    chalmers Repository record for Mitigating label noise in ECG data: A comparative analysis (opens in a new tab)

  4. Towards Robust Deep Learning: Label Noise Modeling, Algorithms, and Applications

    … In the first part, we address instance-dependent label noise by using a tensor factorization–based methodology that models the noise transition process as an instance-dependent decomposition. We also utilize low-rank block-term structures to capture class-specific and instance-specific …

    ucf Repository record for Towards Robust Deep Learning: Label Noise Modeling, Algorithms, and Applications (opens in a new tab)

  5. Mitigating the Effects of Label Noise in Time-Series Sensor Data

    … to learn solutions to real-world problems. Label noise, defined as inaccurate annotations, is one particularly detrimental uncertainty. This issue is more pronounced in time series data, where interpretability is inherently limited. A variety of real-world applications, such as medical …

    texas-state Repository record for Mitigating the Effects of Label Noise in Time-Series Sensor Data (opens in a new tab)

  6. Robust deep learning for computer vision to counteract data scarcity and label noise

    … the model needs to be robust towards data and label noise. Specifically, deep neural networks often require an extensive training set and high-quality, human-annotated labels. However, these data and labels might be expensive or impracticable to obtain. Therefore, in this thesis, we focus on …

    freiburg-diss Repository record for Robust deep learning for computer vision to counteract data scarcity and label noise (opens in a new tab)

  7. Predictions of Periventricular Fazekas Scores on MRI: Addressing Label Noise, Interpretability and Uncertainty

    … modifies the loss function 1) to address label noise caused by inter-rater variability driven by the diverse phenotypes of WMH, and 2) to incorporate the ordinal nature of the Fazekas scores. Therefore, different loss functions are investigated and their models compared. Heatmaps were …

    calgary Repository record for Predictions of Periventricular Fazekas Scores on MRI: Addressing Label Noise, Interpretability and Uncertainty (opens in a new tab)

  8. Instance-Aware Learning in the Presence of Label Noise: An Adaptive Framework for Image Classification

    … Such quality is negatively affected by noisy labels, which can significantly degrade the training process of the models and reduce their accuracy and generalisation capabilities. Traditionally, noisy labels have been viewed as random labelling mistakes, in which the resulting noisy label is …

    adelaide Repository record for Instance-Aware Learning in the Presence of Label Noise: An Adaptive Framework for Image Classification (opens in a new tab)

  9. Automated Cleaning of Identity Label Noise in A Large-scale Face Dataset Using A Face Image Quality Control

    … and thus have many faces with wrong identity labels (outliers). Additionally, the face images in these datasets have different qualities. Since the low quality face images are hard to identify, current automated identity label cleaning methods are not able to detect the identity label error in …

    wvu Repository record for Automated Cleaning of Identity Label Noise in A Large-scale Face Dataset Using A Face Image Quality Control (opens in a new tab)

  10. Reconciling with Noise in Machine Learning for Healthcare

    This thesis explores the challenges presented by label noise in machine learning (ML) for health. Label noise is unavoidable in real-world data; it can arise from variability in measurement, human annotation errors, and aleatoric uncertainty in the ground truth. Ignoring label noise when training …

    toronto-retro Repository record for Reconciling with Noise in Machine Learning for Healthcare (opens in a new tab)

  11. Visual representation learning with deep neural networks under label and budget constraints

    … done in the area of semi-supervised learning, label noise, and budgeted training for deep learning approaches to computer vision. The improvements seen in computer vision since the successful introduction of deep learning rely on the availability of large amounts of labeled data and long …

    dcu Download PDF for Visual representation learning with deep neural networks under label and budget constraints (opens in a new tab)

  12. Data driven approaches to address inaccurate nosology in mental health from neuroimaging data

    … research addresses the pervasive challenge of label noise in machine learning, particularly in sensitive domains like medical applications and psychiatry. Label noise, stemming from sources such as inadequate information and human error, poses a significant threat to the accuracy of …

    gatech Repository record for Data driven approaches to address inaccurate nosology in mental health from neuroimaging data (opens in a new tab)

  13. Text Classification with Noisy Class Labels

    … on the problem of text classification with noise in the labels of the training data. Label noise can have many potential consequences, such as decreasing the model's accuracy and increasing the model's complexity. Designing learning algorithms that help maximize a desired performance measure …

    carleton Repository record for Text Classification with Noisy Class Labels (opens in a new tab)

  14. ROBUST MACHINE LEARNING FOR COMPUTER VISION IN NAVAL APPLICATION

    … However, real-world datasets may be affected by label noise introduced either through random inaccuracies or deliberate adversarial attacks, both of which can negatively impact the accuracy of machine learning models. Our innovative approach employs Rockafellian Risk Minimization (RRM) to combat …

    nps Repository record for ROBUST MACHINE LEARNING FOR COMPUTER VISION IN NAVAL APPLICATION (opens in a new tab)

  15. The Utility of Validation Sets for Meta-learning Methods for Noisy-Label and Imbalanced Learning Problems

    … dataset that are likely to be contaminated with label noise. Unfortunately, deep neural networks with their high capacity can easily overfit to those training samples, resulting in a deterioration in terms of prediction performance. Moreover, the presence of noisy-labeled data can aggravate label …

    adelaide Repository record for The Utility of Validation Sets for Meta-learning Methods for Noisy-Label and Imbalanced Learning Problems (opens in a new tab)

  16. Inspecting the Machine Learning Pipeline: from Weak Supervision to Explainability

    … concern in supervised learning is the quality of labels. For example,<br/>labels are expected to not be ideal in situations where the data is harvested directly from the web<br/>[36, 127]. In general, this is a result of annotations not being carried out by domain experts.<br/>In the first part of …

    bristol Repository record for Inspecting the Machine Learning Pipeline: from Weak Supervision to Explainability (opens in a new tab) Download PDF for Inspecting the Machine Learning Pipeline: from Weak Supervision to Explainability (opens in a new tab)

  17. Learning Models For Corrupted Multi-Dimensional Data: Fundamental Limits And Algorithms

    … datasets such as datasets with unreliable labels and noisy multi-dimensional signals with or without missing information have becoming a central necessity. We are not always fortunate enough to get noise-free datasets for developing classification and representation models. Though there is …

    wayne-thes Repository record for Learning Models For Corrupted Multi-Dimensional Data: Fundamental Limits And Algorithms (opens in a new tab)

  18. Μηχανές διανυσμάτων υποστήριξης για θορυβώδεις και ασαφείς ετικέτες

    … the problem of pattern recognition with noisy labels or fuzzy training instances. Label noise refers to wrong label assignments whereas fuzziness refers to instances with different membership values for their class. Such problems can be solved effectively by modelling the noise or the fuzziness …

    greece Repository record for Μηχανές διανυσμάτων υποστήριξης για θορυβώδεις και ασαφείς ετικέτες (opens in a new tab)

  19. Supervised learning with random labelling errors

    … supervised learning from a training set of labelled examples assumes that the labels are correct. But in reality labelling errors may originate, for example, from human mistakes, diverging human opinions, or errors of the measuring instruments. In such cases the training set is misleading …

    birmingham Download PDF for Supervised learning with random labelling errors (opens in a new tab)

Page 1 of 6