Advanced search

Found 3 essays matching the above criteria.

  1. 1. Investigating Relations between Regularization and Weight Initialization in Artificial Neural Networks

    University essay from Lunds universitet/Beräkningsbiologi och biologisk fysik - Genomgår omorganisation

    Author : Rasmus Sjöö; [2022]
    Keywords : Artificial Neural Networks; L1 Regularization; L2 Regularization; Loss Function; Maximum Likelihood; Regularization Strength Synthetic Data Generation; Weight Initialization; Physics and Astronomy;

    Abstract : L2 regularization is a common method used to prevent overtraining in artificial neural networks. However, an issue with this method is that the regularization strength has to be properly adjusted for it to work as intended. This value is usually found by trial and error which can take some time, especially for larger networks. READ MORE

  3. 2. Predicting Subprime Customers' Probability of Default Using Transaction and Debt Data from NPLs

    University essay from KTH/Matematisk statistik

    Author : Lai-Yan Wong; [2021]
    Keywords : Credit Scoring Model; Probability of Default; Payment Behaviour; Subprime Customer; Non-performing Loan; Logistic Regression; Regularization; Feature Selection; Kreditvärdighetsmodell; Sannolikhet för Fallissemang; Betalningsbeteende; Högriskkunder; Nödlidandelån; Logistik Regression; Regularisering; Variabelselektion;

    Abstract : This thesis aims to predict the probability of default (PD) of non-performing loan (NPL) customers using transaction and debt data, as a part of developing credit scoring model for Hoist Finance. Many NPL customers face financial exclusion due to default and therefore are considered as bad customers. READ MORE

  4. 3. Sparse Linear Modeling of Speech from EEG

    University essay from Linköpings universitet/Reglerteknik; Linköpings universitet/Tekniska högskolan

    Author : Mattias Tiger; [2014]
    Keywords : EEG; In-Ear; Sparse; L1-regularization; Least Squares; FIR; Spectrogram; Machine Learning;

    Abstract : For people with hearing impairments, attending to a single speaker in a multi-talker background can be very difficult and something which the current hearing aids can barely help with. Recent studies have shown that the audio stream a human focuses on can be found among the surrounding audio streams, using EEG and linear models. READ MORE