Sökning: "hyperparameter-selection"

Hittade 3 avhandlingar innehållade ordet hyperparameter-selection.

  1. 1. Towards Scalable Machine Learning with Privacy Protection

    Författare :Dominik Fay; Mikael Johansson; Tobias J. Oechtering; Jens Sjölund; Antti Honkela; KTH; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Machine Learning; Privacy; Differential Privacy; Dimensionality Reduction; Image Segmentation; Hyperparameter Selection; Adaptive Optimization; Privacy Amplification; Importance Sampling; Maskininlärning; Dataskydd; Differentiell Integritet; Dimensionsreducering; Bildsegmentering; Hyperparameterurval; Adaptiv Optimering; Integritetsförstärkning; Importance Sampling; Datalogi; Computer Science; Informations- och kommunikationsteknik; Information and Communication Technology;

    Sammanfattning : The increasing size and complexity of datasets have accelerated the development of machine learning models and exposed the need for more scalable solutions. This thesis explores challenges associated with large-scale machine learning under data privacy constraints. LÄS MER

  3. 2. Group-Sparse Regression : With Applications in Spectral Analysis and Audio Signal Processing

    Författare :Ted Kronvall; Statistical Signal Processing Group; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; sparse regression; group-sparsity; statistical modeling; regularization; hyperparameter-selection; spectral analysis; audio signal processing; classification; localization; multi-pitch estimation; chroma; convex optimization; ADMM; cyclic coordinate descent; proximal gradient;

    Sammanfattning : This doctorate thesis focuses on sparse regression, a statistical modeling tool for selecting valuable predictors in underdetermined linear models. By imposing different constraints on the structure of the variable vector in the regression problem, one obtains estimates which have sparse supports, i.e. LÄS MER

  4. 3. Efficient training of interpretable, non-linear regression models

    Författare :Oskar Allerbo; Göteborgs universitet; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; sparse regression; kernel regression; neural network regression; early stopping; bandwidth selection;

    Sammanfattning : Regression, the process of estimating functions from data, comes in many flavors. One of the most commonly used regression models is linear regression, which is computationally efficient and easy to interpret, but lacks in flexibility. LÄS MER