Essays about: "L2 regularization strength"

Found 2 essays containing the words L2 regularization strength.

  1. 1. Optimizing L2-regularization for Binary Classification Tasks

    University essay from Lunds universitet/Beräkningsbiologi och biologisk fysik

    Author : Oskar Bolinder; [2022]
    Keywords : Machine learning; Overtraining; L2-regularization; Model selection; Binary classification; Physics and Astronomy;

    Abstract : An Artificial Neural Network (ANN) is a type of machine learning algorithm with widespread usage. When training an ANN, there is a risk that it gets overtrained and cannot solve the task for new data. Methods to prevent this, such as L2-regularization, introduce hyperparameters that are time-consuming to optimize. READ MORE

  2. 2. Prediction of appropriate L2 regularization strengths through Bayesian formalism

    University essay from Lunds universitet/Beräkningsbiologi och biologisk fysik; Lunds universitet/Institutionen för astronomi och teoretisk fysik

    Author : Alexander Degener; [2022]
    Keywords : Machine learning; Artificial Neural Network; L2 regularization strength; Bayesian formalism; Classification tasks; Physics and Astronomy;

    Abstract : This paper proposes and investigates a Bayesian relation between optimal L2 regularization strengths and the number of training patterns and hidden nodes used for an artificial neural network. The results support the proposed dependence for number of training patterns, while the dependence on hidden architecture was less clear. READ MORE