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 11 of 11 for “"Parameter reduction"”.

  1. Parameter reduction in deep learning and classification

    … much work has been carried out on dimensionality reduction, the first part of our work focuses on using dominancy between features in the aim to select a relevant subset of informative features. We propose 3 variations, with different benefits, including fast filter features selection and a hybrid …

    cork Repository record for Parameter reduction in deep learning and classification (opens in a new tab)

  2. REGULARIZATION ON MACHINE LEARNING

    … of Drop-Activation can be considered as implicit parameter reduction. Also, our theoretical analysis verifies its capability to be used together with Batch Normalization (Ioffe and Szegedy 2015). We perform Drop-Activation on the benchmark datasets and show that the performance of popular networks …

    nus Repository record for REGULARIZATION ON MACHINE LEARNING (opens in a new tab)

  3. Composite load modeling for power systems: Model reduction, identification, and application to conservation voltage reduction

    … the high model order and the large number of parameters raise new challenges to power system studies such as high computational burden in large-scale simulation and large search space in parameter identification. To overcome these challenges, it is imperative to develop a systematic …

    iastate Repository record for Composite load modeling for power systems: Model reduction, identification, and application to conservation voltage reduction (opens in a new tab)

  4. Functional analysis of low grade glioma genetic variants using statistics and physics-inspired deep learning methods

    … (TT-decomposition) to neural network parameter reduction and demonstrated that the reduced convolutional neural network performed well. This work helps understand the molecular mechanisms underlying genetic risk factors of low grade glioma. The CNN and TT-decomposition-based deep …

    uiuc Repository record for Functional analysis of low grade glioma genetic variants using statistics and physics-inspired deep learning methods (opens in a new tab)

  5. Spectral Geometry for Deep Learning: Compression and Hallucination Detection via Random Matrix Theory

    … ResNet, and benchmark datasets demonstrate major parameter reduction with minimal accuracy loss, yielding faster inference and significant energy savings. These contributions establish spectral geometry as a principled lens for both diagnosing uncertainty and guiding compression. By linking …

    uic

  6. Variation-Derived Chip Security And Accelerated Simulation Of Variations

    … simulation under the effects of parameter variations. Threshold voltage approximation of parameter variations can help accelerate simulations, but it comes with unknown losses in quality. Instead, we propose a parameter reduction technique designed to minimize quality loss through …

    purdue-thes Repository record for Variation-Derived Chip Security And Accelerated Simulation Of Variations (opens in a new tab)

  7. Neural network based learnings in support of two application domains

    … applications tend to be complex, with excessive parameters and heavy calculation costs. Hence, we propose a lightweight NN for MEF, consisting mainly of depthwise and pointwise convolution. Experimental results show that this proposed technique could generate HDR images in extremely exposed …

    calgary Repository record for Neural network based learnings in support of two application domains (opens in a new tab)

  8. Reconfigurable modelling of physically based systems: Dynamic modelling and optimisation for product design and development applied to the automotive drivetrain system.

    … optimisation algorithm that seeks to eliminate parameters that are of little or no significance to a simulation is developed. Eliminations are made on the basis of an energy analysis which determines the activity of a number of energy elements. Low activity elements are said to be of less …

    bradford Repository record for Reconfigurable modelling of physically based systems: Dynamic modelling and optimisation for product design and development applied to the automotive drivetrain system. (opens in a new tab)

  9. Low-Complexity Structured Neural Networks and Their Usage in Image and Signal Processing

    … due to high computational costs, large parameter counts, and reliance on backpropagation, which restricts their application in resource-constrained and real-time settings. To address these challenges, this thesis proposes three structured neural network (NN) architectures grounded in the …

    embry-riddle Repository record for Low-Complexity Structured Neural Networks and Their Usage in Image and Signal Processing (opens in a new tab)

  10. Improving the robustness of GPS direct position estimation

    … and vector tracking. In addition, since the parameter of interest is the navigation solution, DPE provides a natural framework for directly incorporating additional navigation information. The contribution of this thesis is to design and experimentally validate algorithms for deeply …

    uiuc Repository record for Improving the robustness of GPS direct position estimation (opens in a new tab)

  11. Reduced order modelling of bone resorption and formation.

    … been studied different within wide range of rate parameters. The approach to the model validation has been considered, including a statistical approach and parameter reduction approach. From a validation perspective the cellular class of modes is preferable since it has fewer parameters to …

    de-montfort Repository record for Reduced order modelling of bone resorption and formation. (opens in a new tab)