Essays about: "Regularisering"

Showing result 1 - 5 of 12 essays containing the word Regularisering.

  1. 1. Neural Network Regularization for Generalized Heart Arrhythmia Classification

    University essay from Blekinge Tekniska Högskola/Institutionen för datavetenskap; Blekinge Tekniska Högskola/Institutionen för datavetenskap

    Author : Oliver Glandberger; Daniel Fredriksson; [2020]
    Keywords : Arrhythmia; Classification; Regularization; Scaleogram; TensorFlow; Arytmi; Klassificering; Regularisering; Spektrogram; TensorFlow;

    Abstract : Background: Arrhythmias are a collection of heart conditions that affect almost half of the world’s population and accounted for roughly 32.1% of all deaths in 2015. More importantly, early detection of arrhythmia through electrocardiogram analysis can prevent up to 90% of deaths. READ MORE

  2. 2. New Variants of Nonnegative Matrix Factorization with Application to Speech Coding and Speech Enhancement

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Pedro Jafeth Villasana Tinajero; [2019]
    Keywords : ;

    Abstract : In this thesis, new variants of nonnegative matrix factorization (NMF) based ona convolutional data model, -divergence and sparsication are developed andanalyzed. These NMF variants are collectively referred to as -CNMF. Commonsparsication techniques such as L1-norm minimization and elastic net arediscussed and a new regularizer is proposed. READ MORE

  3. 3. Exploring the LASSO as a Pruning Method

    University essay from Lunds universitet/Beräkningsbiologi och biologisk fysik

    Author : Leo Ekbom; [2019]
    Keywords : neural networks; pruning; lasso; group lasso; obd; Physics and Astronomy;

    Abstract : In this study, the efficiency of various pruning algorithms were investigated, with an emphasis on regularization methods. Pruning is a method which aims to remove excess objects from a neural network. READ MORE

  4. 4. Solving an inverse problem for an elliptic equation using a Fourier-sine series.

    University essay from Linköpings universitet/Matematiska institutionen

    Author : Olivia Linder; [2019]
    Keywords : Regularization; ill-posed problem; Fourier-sine series; Regularisering; illaställt problem; Fouriersinusserie;

    Abstract : This work is about solving an inverse problem for an elliptic equation. An inverse problem is often ill-posed, which means that a small measurement error in data can yield a vigorously perturbed solution. Regularization is a way to make an ill-posed problem well-posed and thus solvable. READ MORE

  5. 5. Complexity evaluation of CNNs in tightly coupled hybrid recommender systems

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Patrik Ingverud; [2018]
    Keywords : recommender systems; convolutional neural network; matrix factorization;

    Abstract : In this report we evaluated how the complexity of a Convolutional Neural Network (CNN), in terms of number of filters, size of filters and dropout, affects the performance on the rating prediction accuracy in a tightly coupled hybrid recommender system. We also evaluated the effect on the rating prediction accuracy for pretrained CNNs in comparison to non-pretrained CNNs. READ MORE