Essays about: "L2 regularization strength"
Found 2 essays containing the words L2 regularization strength.
University essay from Lunds universitet/Beräkningsbiologi och biologisk fysik
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
University essay from Lunds universitet/Beräkningsbiologi och biologisk fysik; Lunds universitet/Institutionen för astronomi och teoretisk fysik
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