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 45 for “"Labeled and unlabeled data"”.

  1. Addressing the data challenge in automatic drum transcription with labeled and unlabeled data

    … impeded by the lack of a meaningful amount of labeled data to support the data-driven algorithms. To address this data challenge in ADT, this work presents three approaches. First, a dataset for ADT tasks is created using a semi-automatic process that minimizes the workload of human annotators. …

    gatech Repository record for Addressing the data challenge in automatic drum transcription with labeled and unlabeled data (opens in a new tab)

  2. Improving the performance of automatic target recognition using data augmentation.

    … a task that aims to recognize targets based on data obtained from visual sensors such as Infrared cameras. Machine learning, in particular Deep Learning, has been the dominate approach to solve this task. However, in order to achieve high performance, Deep Learning requires a large amount of …

    louisville Repository record for Improving the performance of automatic target recognition using data augmentation. (opens in a new tab)

  3. Interactive and Incremental Learning via a Multisensory Mobile Robot

    The thesis reports the design and implementation of our scheme for spoken language acquisition. In the thesis, we discuss the available resources and possible pitfalls for the robot project: we discuss the speech communication techniques that can be or cannot be used in our project; we choose the …

    uiuc Repository record for Interactive and Incremental Learning via a Multisensory Mobile Robot (opens in a new tab)

  4. Polyglot Text Classification with Neural Document Models

    Sometimes, annotating data for text classification is expensive, so one must rely on techniques like parameter sharing and semi-supervised learning to improve classification performance in low-resource environments. In this thesis, I combine a generative, neural document model (Card et. al, 2018) …

    washington Repository record for Polyglot Text Classification with Neural Document Models (opens in a new tab)

  5. Clustering and feature detection methods for high-dimensional data

    The majority of the real-world data are unlabeled. Moreover, complex characteristics such as high-dimensionality and high variety pose significant analytical challenges. In statistical and machine learning, supervised and unsupervised methods are used to analyze labeled and unlabeled data, …

    gatech Repository record for Clustering and feature detection methods for high-dimensional data (opens in a new tab)

  6. Semi supervised weighted maximum variance dimensionality reduction

    In the recent years, we have huge amounts of data which we want to classify with minimal human intervention. Only few features from the data that is available might be useful in some scenarios. In those scenarios, the dimensionality reduction methods play a major role for extracting useful …

    njit Repository record for Semi supervised weighted maximum variance dimensionality reduction (opens in a new tab)

  7. Weakly Supervised Learning for Musical Instrument Classification

    … models also increase the need for high quality labeled data. For the MIC task, there do not exist such large-scale fully annotated datasets. Instead researchers tend to utilize multi-track data to obtain fine-grained instrument activity annotation. Such datasets are also known as strongly …

    gatech Repository record for Weakly Supervised Learning for Musical Instrument Classification (opens in a new tab)

  8. Learning without labels and nonnegative tensor factorization

    … of the predictors, are typically performed with labeled data. In most cases, obtaining labeled data is costly as it requires manual labeling. On the other hand, unlabeled data is available in abundance. In this thesis, we discuss methods to perform supervised learning tasks with no labeled data. …

    gatech Repository record for Learning without labels and nonnegative tensor factorization (opens in a new tab)

  9. Semisupervised Learning of Classifiers With Application to Human -Computer Interaction

    With the growing use of computers and computing objects in the design of many of the day to day tools that humans use, human-computer intelligent interaction is seen as a necessary step for the ability to make computers better aid the human user. There are many tasks involved in designing good …

    uiuc Repository record for Semisupervised Learning of Classifiers With Application to Human -Computer Interaction (opens in a new tab)

  10. Graph regularized transductive classification on heterogeneous information networks

    … a network composed of multiple types of objects and links. Recently, it has been recognized that strongly-typed heterogeneous information networks are prevalent in the real world. Sometimes, label information is available for some objects. Learning from such labeled and unlabeled data via …

    uiuc Repository record for Graph regularized transductive classification on heterogeneous information networks (opens in a new tab)

  11. Uma proposta de automatização do processo de rotulagem de instâncias em algoritmos de aprendizado semissupervisionado

    … of machine learning that integrates supervised and unsupervised learning mechanisms. In this type of learning, most of training set labels are unknown, while there is a small part of data that has known labels. The semi-supervised learning is attractive because of its potential to use labeled …

    brazil-ufrn Repository record for Uma proposta de automatização do processo de rotulagem de instâncias em algoritmos de aprendizado semissupervisionado (opens in a new tab)

  12. Pusiau prižiūrimo mokymosi metodai kasos vėžiui identifikuoti kompiuterinės tomografijos vaizduose /

    … learning techniques that can leverage both labeled and unlabeled data. The rese arch begins with a literature review, analyzing the fundamentals of semi-supervised learning, its historical development, application challenges in medical image analysis, and the key algorithms considered, the …

    vilnius Repository record for Pusiau prižiūrimo mokymosi metodai kasos vėžiui identifikuoti kompiuterinės tomografijos vaizduose / (opens in a new tab)

  13. Landmine detection using semi-supervised learning.

    Landmine detection is imperative for the preservation of both military and civilian lives. While landmines are easy to place, they are relatively difficult to remove. The classic method of detecting landmines was by using metal-detectors. However, many present-day landmines are composed of little …

    louisville Repository record for Landmine detection using semi-supervised learning. (opens in a new tab)

  14. Development of Attention Guided U-Net for Medical Image Segmentation

    … pivotal role in clinical diagnostics, monitoring and treating diseases. The convolutional neural network, U-Net, was specifically developed for segmentation of medical images in view of its ability to accurately segment with limited training data. Existing U-Net based segmentation networks suffer …

    concordia Download PDF for Development of Attention Guided U-Net for Medical Image Segmentation (opens in a new tab)

  15. Understanding BITCOIN Market Mechanics Using Feature Engineering, Data Modeling, and Forecasting Methods

    Bitcoin (BTC) has emerged as a groundbreaking and influential cryptocurrency, revolutionizing the financial landscape. Traders operating in the Bitcoin market encounter numerous challenges when it comes to making informed decisions due to the inherent volatility of the cryptocurrency market. Given …

    westminster Repository record for Understanding BITCOIN Market Mechanics Using Feature Engineering, Data Modeling, and Forecasting Methods (opens in a new tab) Download PDF for Understanding BITCOIN Market Mechanics Using Feature Engineering, Data Modeling, and Forecasting Methods (opens in a new tab)

  16. Semi-Supervised Deep Learning Approach for Transportation Mode Identification Using GPS Trajectory Data

    … the domain of transportation such as travel demand analysis, transport planning, and traffic management. This thesis aims to identify travelers' transportation modes purely based on their GPS trajectories. First, a segmentation process is developed to partition a user's trip into GPS segments …

    vt Repository record for Semi-Supervised Deep Learning Approach for Transportation Mode Identification Using GPS Trajectory Data (opens in a new tab)

  17. False Textual Information Detection - Towards Building a Truth Machine

    … false information, such as questionable claims and fake news, diffuses fast. Detecting false information is one of the most elusive and long-standing challenges. With social media growing dominant, falsehood can diffuse faster and broader than truth. This calls for building a ``truth machine" …

    houston Repository record for False Textual Information Detection - Towards Building a Truth Machine (opens in a new tab)

  18. Deep Generative Models for Vision, Languages and Graphs

    … remarkable success in modeling various types of data, ranging from vision, languages and graphs etc. They offer flexible and complementary representations for both labeled and unlabeled data. Moreover, they are naturally capable of generating realistic data. In this thesis, novel variations of …

    duke Repository record for Deep Generative Models for Vision, Languages and Graphs (opens in a new tab)

  19. Machine learning for network traffic classification under labeled data and training time constraints

    … classification when constrained by too little labeled data or insufficient time to train models from scratch. Network traffic classification is essential in network security, network management, and application identification. Labeling network traffic data, however, is often time-consuming and …

    colo-mines Repository record for Machine learning for network traffic classification under labeled data and training time constraints (opens in a new tab)

Page 1 of 3