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 892 for “"data augmentation"”.

  1. Counterfactual Data Augmentation for Regression

    Data-driven modeling in real-world regression tasks often suffers from limited training samples, high collection costs, and noisy observations. While data augmentation has revolutionized fields such as computer vision and natural language processing by leveraging domain-specific symmetries, …

    waterloo Repository record for Counterfactual Data Augmentation for Regression (opens in a new tab)

  2. Natural Audio Data Augmentation Techniques

    … von Datensätzen, ein Prozess, der auch als Data Augmentation bekannt ist und dazu dient, ein maschinelles Lernmodell zu trainieren und zu bewerten, wird seit langem angewendet und erforscht. Diese Arbeit befasst sich mit einem Problem der Data Augmentation im Bereich der Audioverarbeitung. …

    humboldt-diss Repository record for Natural Audio Data Augmentation Techniques (opens in a new tab)

  3. Domain adaptation via data augmentation

    Deep learning (DL) models require large labeled datasets for training. Practitioners often need to adapt an existing DL model to a different domain. For instance, a practitioner in a company developing autonomous vehicles may need to adapt an object detection model trained over images collected …

    gatech Repository record for Domain adaptation via data augmentation (opens in a new tab)

  4. Data Augmentation with Seq2Seq Models

    … results in a significantly expanded training dataset and vocabulary size, but has slightly worse performance when tested on the validation split. Although not as fruitful as we had hoped, our work highlights additional avenues for investigation into selecting more optimal model parameters and …

    vt Repository record for Data Augmentation with Seq2Seq Models (opens in a new tab)

  5. Data Augmentation For Text Classification Tasks

    … power and the growing availability of large datasets, neural networks have achieved state of the art results in many natural language process- ing (NLP) and computer vision (CV) tasks. These models require a large number of training examples that are balanced between classes, but in many …

    waterloo Repository record for Data Augmentation For Text Classification Tasks (opens in a new tab)

  6. Genomic Data Augmentation with Variational Autoencoder

    … to make such predictions. However, biomedical datasets, including genomic datasets, often have disproportionately more samples from people of European ancestry than people of other ethnic or racial groups, which can cause machine learning methods to perform better on the European samples than …

    temple Repository record for Genomic Data Augmentation with Variational Autoencoder (opens in a new tab)

  7. Improving Image Classification Through Generative Data Augmentation

    … of copious amounts of labelled training data. Unfortunately, medical datasets are typically small due to privacy constraints and the large cost associated with annotating the data. To ameliorate this limitation, a training scheme is developed in this thesis which can operate on …

    calgary Repository record for Improving Image Classification Through Generative Data Augmentation (opens in a new tab)

  8. Medical Image Data Augmentation Using Style Transfer

    … are constrained by the need for large, balanced datasets. Medical images are often very expensive to annotate and require the valuable time of experts. Data augmentation is often used as an automated way of adding additional instances to address this problem. In this thesis, we propose a method …

    buffalo Repository record for Medical Image Data Augmentation Using Style Transfer (opens in a new tab)

  9. Automatic Machine Learning in Optimization and Data Augmentation

    … recognized by the AI community: optimization and data augmentation. The proposed AutoML workflow in optimization can automatically adjust the learning rate for deep learning tasks. It monitors the signals generated during optimization and dynamically changes the learning rate based on the signal …

    oklahoma-thes Repository record for Automatic Machine Learning in Optimization and Data Augmentation (opens in a new tab) Restricted access

  10. Representation Learning and Data Augmentation in Forensic Comparison

    … automatically learned image representations and data augmentation.Representation learning is about training a system to learn semantic representations from raw data, such as raw image data. The task of forensic comparison requires the representation learned to have certain interpretability, be …

    buffalo Repository record for Representation Learning and Data Augmentation in Forensic Comparison (opens in a new tab)

  11. Enhanced Finger Movement Detection Using sEMG by Data Augmentation

    … in classifying individual finger movements is data sparsity resulting from device availability, acquisition time, and patient privacy laws. To alleviate the problem of limited training data, we propose to synthetically augment the training data. Although some sEMG data augmentation methods have …

    washington Repository record for Enhanced Finger Movement Detection Using sEMG by Data Augmentation (opens in a new tab)

  12. Data augmentation for attack detection on IoT Telehealth Systems

    … that employs several machine learning and data analysis techniques to detect those attacks. We evaluate the effectiveness of the proposed framework using two publicly available datasets from real-world scenarios. These datasets contain a variety of attacks with different characteristics. …

    uvic Repository record for Data augmentation for attack detection on IoT Telehealth Systems (opens in a new tab)

  13. Application of data augmentation techniques in metabolomics correlation network

    … hampered by the lack of expansive, high-quality datasets- a recurring challenge in clinical metabolomics. While machine learning has transformed numerous disciplines by extracting patterns from vast datasets, its application to typically smaller clinical metabolomics datasets remains suboptimal. …

    uvic Repository record for Application of data augmentation techniques in metabolomics correlation network (opens in a new tab)

  14. Using Generative Models for Data Augmentation in Medical Imaging

    Obtaining large amounts of labelled data in medical imaging is hindered by issues like privacy and cost, therefore limiting the gains that can be achieved from Deep Neural Networks (DNNs). A lot of work has shown data augmentation to be an effective strategy for expanding training data leading to …

    rit Repository record for Using Generative Models for Data Augmentation in Medical Imaging (opens in a new tab)

  15. EFFICIENT SIGNAL SYNTHESIS FOR DATA AUGMENTATION USING GENERATIVE AI

    … face increasing demands for diverse training data while operating under computational constraints. State-of-the-art generative models, though effective, often require prohibitive resources, limiting their deployment in real-time or embedded systems. This thesis proposes a computationally …

    rowan Repository record for EFFICIENT SIGNAL SYNTHESIS FOR DATA AUGMENTATION USING GENERATIVE AI (opens in a new tab)

  16. Deep Synthetic Noise Generation for RGB-D Data Augmentation

    … amounts of carefully-corrected ground-truth data to train effectively. Data collection is laborious and time-intensive, especially for large datasets, and generation of ground-truth training data tends to be subject to human error. It might be possible to train an effective method on a …

    byu Repository record for Deep Synthetic Noise Generation for RGB-D Data Augmentation (opens in a new tab) Download PDF for Deep Synthetic Noise Generation for RGB-D Data Augmentation (opens in a new tab)

  17. Data augmentation for the handling of censored spatial data

    … a solution to the analysis of spatial censored data. Spatially dependent data occurs in a variety of applications in which observations are associated with a spatial location. In environmental data, it is not uncommon for measurements of contamination to fall below a level of detection (LOD). …

    iastate Repository record for Data augmentation for the handling of censored spatial data (opens in a new tab)

Page 1 of 45