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 14 of 14 for “"Kernel k-means"”.

  1. Scalable Embeddings for Kernel Clustering on MapReduce

    … for discovering natural groupings in data. The k-means algorithm is the most commonly-used data clustering method, having gained popularity for its effectiveness on various data sets and ease of implementation on different computing architectures. It assumes, however, that data are available in an …

    waterloo Repository record for Scalable Embeddings for Kernel Clustering on MapReduce (opens in a new tab)

  2. On k-means Clustering for Complex High-Dimensional Data

    … following article: Guan X., Terada Y.. Sparse kernel k-means for high-dimensional data. Pattern Recognition 144, 109873 (2023); https://doi.org/10.1016/j.patcog.2023.109873.

    osaka Repository record for On k-means Clustering for Complex High-Dimensional Data (opens in a new tab) Download PDF for On k-means Clustering for Complex High-Dimensional Data (opens in a new tab)

  3. Low rank methods for optimizing clustering

    … where this arises. First, we consider the NEO-K-Means (Non-Exhaustive, Overlapping K-Means) objective as a way to address overlapping and outliers in an integrated fashion. Optimizing this discrete objective is NP-hard, and even though there is a convex relaxation of the objective, …

    purdue-thes Repository record for Low rank methods for optimizing clustering (opens in a new tab)

  4. Nonparametric Bayesian analysis of some clustering problems

    … work (Dhillon, 2001) showing the equivalence of kernel k-means clustering and certain graph cutting algorithms. It is shown that loss functions similar to the kernel k-means naturally arise in this model, and the minimization of associated posterior risk comprises an effective graph cutting …

    tamu Repository record for Nonparametric Bayesian analysis of some clustering problems (opens in a new tab)

  5. Τεχνικές ομαδοποίησης και ταξινόμησης με εφαρμογές στην ανθρωποκεντρική ανάλυση εικόνων και εικονοσειρών

    … in this field concerns the trimming of the kernel matrix used by the kernel k-means algorithm. The proposed trimming algorithm attempts to estimate the cardinality of the cluster that each sample belongs to and trims the corresponding matrix row based on this estimation. This results in the …

    greece Repository record for Τεχνικές ομαδοποίησης και ταξινόμησης με εφαρμογές στην ανθρωποκεντρική ανάλυση εικόνων και εικονοσειρών (opens in a new tab)

  6. Computational improvements to clustering methods

    … of settings.We start with the extension of k-means clustering, kernel k-means, which allows for the clustering of non-spherical data. Computationally efficient methods are introduced, which are shown in simulations to outperform the standard method. Next, we focus on model-based clustering, …

    iastate Repository record for Computational improvements to clustering methods (opens in a new tab)

  7. A Semi-Supervised Approach for Kernel-Based Temporal Clustering

    … proposes a process to adapt and transform two kernel-based methods into semi-supervised temporal clustering methods. The proposed process is exclusive to kernel-based clustering methods, and is based on two concepts. First, it uses the idea of instance-level constraints, in the form of …

    waterloo Repository record for A Semi-Supervised Approach for Kernel-Based Temporal Clustering (opens in a new tab)

  8. Clustering methods based on deep learning and unimodality testing

    … i) partitional clustering in both Euclidean and kernel spaces, ii) unimodality-based clustering, which incorporates the concept of unimodality into the clustering process, and iii) deep clustering, which leverages the representational power of deep learning methods. We first introduce global …

    greece Repository record for Clustering methods based on deep learning and unimodality testing (opens in a new tab)

  9. Classification and Evaluation of Player Performance in Netball using Cluster Analysis

    … linkage, with a best accuracy of just 38%. Kernel k-means, which was designed to be an improvement on ordinary k-means, also performed poorly (59%). In the final stage of the project there were 3-4 player types successfully identified within each position, providing insight into how …

    auckland-ms Repository record for Classification and Evaluation of Player Performance in Netball using Cluster Analysis (opens in a new tab)

  10. Large-scale clustering: algorithms and applications

    … we present an efficient, high-quality multilevel kernel-based graph clustering algorithm, which outperforms previous state-of-the-art spectral methods in quality and runs hundreds or even thousands of times faster. Our multilevel graph clustering algorithm is based on a theoretical connection with …

    texas Repository record for Large-scale clustering: algorithms and applications (opens in a new tab)

  11. Scalable kernel methods for machine learning

    … increasingly powerful and scalable techniques. Kernel methods, which generalize linear learning methods to non-linear ones, have become a cornerstone for much of the recent work in machine learning and have been used successfully for many core machine learning tasks such as clustering, …

    texas Repository record for Scalable kernel methods for machine learning (opens in a new tab)

  12. Higher-order Losses and Optimization for Low-level and Deep Segmentation

    … or graph-based clustering objectives, such as kernel K-means and normalized cut. This theoretical understanding inspires our new segmentation algorithms avoiding such biases. The third contribution of the thesis is a new optimization algorithm addressing the limitations of gradient descent in …

    waterloo Repository record for Higher-order Losses and Optimization for Low-level and Deep Segmentation (opens in a new tab)

  13. Enhancing Neural Network Performance through SHAP-based Latent Class Integration

    … clusters the resulting SHAP vectors using kernel k-means, and then incorporates the resulting cluster labels and SHAP values into a downstream neural network. SHAP values are used both to guide an attention mechanism and as latent embeddings via clustered group membership. Across multiple …

    ku Repository record for Enhancing Neural Network Performance through SHAP-based Latent Class Integration (opens in a new tab)

  14. Clustering using similarity and kernel matrices

    … sources and/or feature spaces and iii) multiple kernel learning, where a kernel that suits the data is learned together with the cluster assignments. Usually, the kernel is parametrized as a combination of some predefined kernels, called basis kernels, and we wish to infer appropriate values for …

    greece Repository record for Clustering using similarity and kernel matrices (opens in a new tab)