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 5 of 5 for “"k-nn graph"”.

  1. Graph-based Learning of Manifold Diffusion and Time-Series Modeling

    <p>This thesis focuses on graph-based methods, providing both theoretical analysis of graph Laplacians under the manifold setting and practical applications to time-series data analysis.</p><p>%The first part of the thesis presents an improved convergence rate for $k$-nearest neighbor ($k$NN) graph …

    duke Repository record for Graph-based Learning of Manifold Diffusion and Time-Series Modeling (opens in a new tab)

  2. On Some Fundamental Aspects of Learning in Artificial Neural Networks and Universal Channel Codes

    … for image classification, and (2) using a channel code for universal communication at capacity. For the classification problem, we aim to develop a better understanding of what representations each layer of the network learns. In particular, we compare the higher-layer activations of two …

    cornell Repository record for On Some Fundamental Aspects of Learning in Artificial Neural Networks and Universal Channel Codes (opens in a new tab)

  3. Local selection of features and its applications to image search and annotation

    … image retrieval and automated image annotation. However, due to the existence of noisy or irrelevant features, errors introduced into similarity measurements are detrimental to the neighborhood quality of data objects. One way to alleviate the negative impact of noisy features is to …

    njit Repository record for Local selection of features and its applications to image search and annotation (opens in a new tab)

  4. SAR Moving Target Detection with Colorized Subaperture Imagery via Graph Partitioning

    … spatial frequency domain to create a three channel image. The advantage with this method compared to video SAR techniques is to preserve cross-range resolution for multilook speckle reduction. After CSI processing, clutter within the image is colored when the return of energy is not uniform …

    rit Repository record for SAR Moving Target Detection with Colorized Subaperture Imagery via Graph Partitioning (opens in a new tab)

  5. Improving k-nn search and subspace clustering based on local intrinsic dimensionality

    … contributions: First, this dissertation proposes NNWID-Descent, a similarity graph construction method that utilizes the support-weighted ID criterion to identify and retain relevant features locally for each object and enhance the overall graph quality. Second, with the aim to improve the …

    njit Repository record for Improving k-nn search and subspace clustering based on local intrinsic dimensionality (opens in a new tab)