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 8 of 8 for “"Shift Invariance"”.

  1. Generative models for neural time series with structured domain priors

    … priors/constraints, such as Gaussian process, shift-invariance, sparsity, and smoothness, among many others. It is demonstrated in the thesis that the Bayesian approach with careful integration of these constraints produces results/structures in the data that are not only intepretable but also …

    mit Repository record for Generative models for neural time series with structured domain priors (opens in a new tab)

  2. Tensor formulations for the modelling of discrete-time nonlinear and multidimensional systems.

    … reduce the computational complexity by assuming shift-invariance. Based on the 2-D lattice, a new nonlinear lattice model is developed. The model is capable of updates in the nonlinear as well as time order.

    nps Repository record for Tensor formulations for the modelling of discrete-time nonlinear and multidimensional systems. (opens in a new tab)

  3. Beurling-Lax Representations of Shift-Invariant Spaces, Zero-Pole Data Interpolation, and Dichotomous Transfer Function Realizations: Half-Plane/Continuous-Time Versions

    Given a full-range simply-invariant shift-invariant subspace <i>M</i> of the vector-valued <i>L<sup>2</sup></i> space on the unit circle, the classical Beurling-Lax-Halmos (BLH) theorem obtains a unitary operator-valued function <i>W</i> so that <i>M</i> may be represented as the image of of the …

    vt Repository record for Beurling-Lax Representations of Shift-Invariant Spaces, Zero-Pole Data Interpolation, and Dichotomous Transfer Function Realizations: Half-Plane/Continuous-Time Versions (opens in a new tab)

  4. Low-complexity methods for image and video watermarking

    … wavelets (perfect reconstruction, approximate shift invariance and good directional selectivity). Our methods use these characteristics to create watermarks that are robust to geometric distortions and lossy compression. The proposed schemes are simple to implement and outperform comparable …

    ubc Repository record for Low-complexity methods for image and video watermarking (opens in a new tab)

  5. Wavelet Transforms for Stereo Imaging

    … and dense disparity map outputs. After the shift invariance property of various wavelet transforms is identified, the main contributions of the thesis are made in developing and evaluating two wavelet approaches (the dyadic wavelet transform and complex wavelet transform) for solving the …

    southwales Repository record for Wavelet Transforms for Stereo Imaging (opens in a new tab)

  6. Design And Assessment Of Compact Optical Systems Towards Special Effects Imaging

    … linear systems, without any assumptions for shift invariance, can be modeled and analyzed.

    ucf

  7. New contributions on image fusion and compression based on space-frecuency representations = Nuevas contribuciones en fusión y compresión de imágenes basadas en representaciones espacio-frecuenciales

    … high selectivity in orientation and scalability, shift-invariance, self-invertibility and complex de_nition confers e_ciency, versatility and robustness against noise and a low presence of artifacts. Further on, the tight similarity of overcomplete log-Gabor _lters to the cortical area V1, …

    upm Repository record for New contributions on image fusion and compression based on space-frecuency representations = Nuevas contribuciones en fusión y compresión de imágenes basadas en representaciones espacio-frecuenciales (opens in a new tab)

  8. Sampling, non-linearities and scales: rethinking convolutional neural networks from a signal processing perspective

    Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-02-04 without embargo terms

    uiuc Repository record for Sampling, non-linearities and scales: rethinking convolutional neural networks from a signal processing perspective (opens in a new tab)