Sökning: "Adaptive Sparsity"

Hittade 3 uppsatser innehållade orden Adaptive Sparsity.

  1. 1. Modelling synaptic rewiring in brain-like neural networks for representation learning

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Kunal Bhatnagar; [2023]
    Nyckelord :Adaptive Sparsity; Computational Neuroscience; Rewiring; Structural Plasticity; Brain-like Computing; Neural Networks; Hebbian Learning; Adaptiv gleshet; beräkningsneurovetenskap; omkoppling; strukturell plasticitet; Hjärnliknande beräkning; Neurala Nätverk; Hebbskt lärande;

    Sammanfattning : This research investigated the concept of a sparsity method inspired by the principles of structural plasticity in the brain in order to create a sparse model of the Bayesian Confidence Propagation Neural Networks (BCPNN) during the training phase. This was done by extending the structural plasticity in the implementation of the BCPNN. LÄS MER

  3. 2. Exploiting the Overtones in Online Localization of Sound Sources

    Master-uppsats, Lunds universitet/Matematisk statistik

    Författare :David Sundström; [2022]
    Nyckelord :Multi-pitch estimation; localization; block sparsity; sparse recursive least squares; online estimation; ADMM; adaptive dictionary; Mathematics and Statistics;

    Sammanfattning : Localization of multiple sound sources from a microphone array is a challenging task that has been a research topic for decades. The challenges stem from the diversity of acoustic contexts due to reverberation and disturbances. LÄS MER

  4. 3. Solving Sudoku by Sparse Signal Processing

    Master-uppsats, KTH/Signalbehandling

    Författare :MUHAMMAD MOHSIN ABBASI; [2015]
    Nyckelord :;

    Sammanfattning : Sudoku is a discrete constraints satisfaction problem which is modeled as an underdetermined linear system. This report focuses on applying some new signal processing approaches to solve sudoku and comparisons to some of the existing approaches are implemented. LÄS MER