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 24 for “"Unsupervised Feature Learning"”.

  1. Automated image classification via unsupervised feature learning by K-means

    … has grown rapidly in the field of machine learning. Many methods have already been implemented for image classification. Among all these methods, best results have been reported by neural network-based techniques. One of the most important steps in automated image classification is feature …

    iupui Repository record for Automated image classification via unsupervised feature learning by K-means (opens in a new tab)

  2. Unsupervised Feature Learning for Point Cloud by Contrasting and Clustering with Graph Convolutional Neural Network

    … large-scale point cloud datasets, we propose an unsupervised learning approach to learn features from unlabeled point cloud ”3D object” dataset by using part contrasting and object clustering with GNNs. In the contrast learning step, all the samples in the 3D object dataset are cut into two parts …

    cuny Repository record for Unsupervised Feature Learning for Point Cloud by Contrasting and Clustering with Graph Convolutional Neural Network (opens in a new tab)

  3. Using tactile sensors and IMUs with an unsupervised feature-learning approach for robotic grasp stability assessment

    … robotic grasping using tactile sensors and an unsupervised feature-learning algorithm. Using a test bench and sensors at the Control and Robotics (CoRo) laboratory of the ÉTS, we have developed and tested a series of classifiers to predict the outcome of a robotic grasp. Our method improves …

    ets-quebec Download PDF for Using tactile sensors and IMUs with an unsupervised feature-learning approach for robotic grasp stability assessment (opens in a new tab)

  4. Sparse feature learning for image analysis in segmentation, classification, and disease diagnosis.

    The success of machine learning algorithms generally depends on intermediate data representation, called features that disentangle the hidden factors of variation in data. Moreover, machine learning models are required to be generalized, in order to reduce the specificity or bias toward the …

    louisville Repository record for Sparse feature learning for image analysis in segmentation, classification, and disease diagnosis. (opens in a new tab)

  5. Generative topographic mapping of electroencephalography (EEG) data

    … Topographic Mapping (GTM) assumes that the features of high dimensional data can be described by a few variables (usually 1 or 2). Based on this assumption, the GTM trains unsupervised on the high dimensional data to find these variables from which the features can be generated. The …

    colostate Repository record for Generative topographic mapping of electroencephalography (EEG) data (opens in a new tab)

  6. Modifying sparse coding to model imbalanced datasets

    … explore the use of sparse coding as a tool for unsupervised feature learning to more effectively model imbalanced datasets. Traditional sparse coding dictionaries are learned by minimizing the average approximation error between a vector and its sparse decomposition. As such, these dictionaries …

    gatech Repository record for Modifying sparse coding to model imbalanced datasets (opens in a new tab)

  7. Learning Hierarchical Representations For Video Analysis Using Deep Learning

    … been a growing interest in the bio-inspired deep learning models, which has shown impressive results in speech and object recognition. The deep learning models are formed by the composition of multiple non-linear transformations of the data, with the goal of yielding more abstract and ultimately …

    ucf Repository record for Learning Hierarchical Representations For Video Analysis Using Deep Learning (opens in a new tab)

  8. Novel Architectures for Radar Sounder Signals Segmentation: From Convolutional Neural Networks to Quantum-Enhanced Networks

    … are grounded in hybrid supervised deep learning architectures, unsupervised feature learning frameworks, and harnessing quantum machine learning frameworks to automatically segment geological units in the cryosphere subsurface. Firstly, we developed a supervised deep learning …

    trento Repository record for Novel Architectures for Radar Sounder Signals Segmentation: From Convolutional Neural Networks to Quantum-Enhanced Networks (opens in a new tab)

  9. Object Recognition and Semantic Scene Labeling for RGB-D Data

    … in a scalable manner. We also present HMP3D, an unsupervised feature learning approach for 3D point cloud data, and demonstrate that HMP3D can be used to learn hierarchies of features from different attributes including color, gradient, shape, and surface normal orientation. Finally, we present a …

    washington Repository record for Object Recognition and Semantic Scene Labeling for RGB-D Data (opens in a new tab)

  10. Data famine in big data era : machine learning algorithms for visual object recognition with limited training data

    … is not true, especially for areas where machine learning methods are heavily employed, since sufficient high-quality training data doesn't necessarily come with the big data, and it is not easy or sometimes impossible to collect sufficient training samples, which most computational algorithms …

    ubc Repository record for Data famine in big data era : machine learning algorithms for visual object recognition with limited training data (opens in a new tab) Download PDF for Data famine in big data era : machine learning algorithms for visual object recognition with limited training data (opens in a new tab)

  11. Learning Image Segmentation With Relation-Centric Loss And Representation

    … efforts in this direction, with an emphasis on learning to model pixel relationships. We identify three major problems in image understanding and segmentation: (1) The pixel-wise classification based approaches fundamentally lack the sense of object structures and spatial layouts. (2) The lack …

    penn Repository record for Learning Image Segmentation With Relation-Centric Loss And Representation (opens in a new tab)

  12. Clustering: Methodology, hybrid systems, visualization, validation and implementation

    "Unsupervised learning is one of the most important steps of machine learning applications. Besides its ability to obtain the insight of the data distribution, unsupervised learning is used as a preprocessing step for other machine learning algorithm. This dissertation investigates the application …

    must-thes Repository record for Clustering: Methodology, hybrid systems, visualization, validation and implementation (opens in a new tab)

  13. Improving Feature Learning Capability and Interpretability of Unsupervised Neural Networks

    … two-prong. Firstly, the current state of machine learning imposes the need for unsupervised Machine Learning (ML). Secondly, once such models are developed, a deeper understanding of ML models is necessary for humans to adapt and use such models. Real-world systems generate massive amounts of …

    vcu Repository record for Improving Feature Learning Capability and Interpretability of Unsupervised Neural Networks (opens in a new tab)

  14. Automatic Video Analysis for Fisheries Survey Systems

    … to produce accurate shape boundary. Built upon a feature-based temporal matching method, the multiple-target tracking algorithm via Viterbi data association is proposed to overcome the abrupt motion and frequent entrance/exit of targets. In segmentation and tracking with uncontrolled background, a …

    washington Repository record for Automatic Video Analysis for Fisheries Survey Systems (opens in a new tab)

  15. Receptive fields optimization in deep learning for enhanced interpretability, diversity, and resource efficiency.

    In both supervised and unsupervised learning settings, deep neural networks (DNNs) are known to perform hierarchical and discriminative representation of data. They are capable of automatically extracting excellent hierarchy of features from raw data without the need for manual feature engineering. …

    louisville Repository record for Receptive fields optimization in deep learning for enhanced interpretability, diversity, and resource efficiency. (opens in a new tab)

  16. DINO Features for Salient Object Detection

    … and aim to learn the relationship between them. Unsupervised SOD methods in comparison attempt to identify salient objects by solely examining an image. This gives unsupervised methods the advantage of not needing expensive labels which are susceptible to human error. One good place to start an …

    waterloo Repository record for DINO Features for Salient Object Detection (opens in a new tab)

  17. 2022: A Computational Odyssey - Towards a Deeper Understanding of Clustering Streaming Human Activity Recognition Data

    … modalities for deep analysis - pure supervised learning - are limited to the classes provided during training and are incapable of relaying any hidden knowledge residing outside of the trained labels. Unsupervised learning methods, such as clustering, are not only well equipped to handle …

    queens Repository record for 2022: A Computational Odyssey - Towards a Deeper Understanding of Clustering Streaming Human Activity Recognition Data (opens in a new tab)

  18. Deep Learning and Feature Engineering for Human Activity Recognition: Exploiting Novel Rich Learning Representations and Sub-transfer Learning to Boost Practical Performance

    … exists in our knowledge of how domain-specific feature extraction compares to unsupervised feature learning in the latent space of a deep neural network for a range of temporal applications including human activity recognition. This dissertation aims to address this gap specifically for human …

    usf Repository record for Deep Learning and Feature Engineering for Human Activity Recognition: Exploiting Novel Rich Learning Representations and Sub-transfer Learning to Boost Practical Performance (opens in a new tab)

Page 1 of 2