Essays about: "Regularization"
Showing result 21 - 25 of 143 essays containing the word Regularization.
-
21. Improving sample-efficiency of model-free reinforcement learning algorithms on image inputs with representation learning
University essay from Göteborgs universitet/Institutionen för data- och informationsteknikAbstract : Reinforcement learning struggles to solve control tasks on directly on images. Performance on identical tasks with access to the underlying states is much better. READ MORE
-
22. EVALUATING THE EXTENT OF ETHNIC BIASES IN FINBERT AND EXPLORING DEBIASING TECHNIQUES
University essay from Göteborgs universitet / Institutionen för filosofi, lingvistik och vetenskapsteoriAbstract : Language models are becoming increasingly popular. These models can contain social biases about various groups of people in them. The reproduction of biased beliefs can have harmful impacts on the groups they are about. We explore the extent of ethnic biases in the Finnish language model FinBERT. READ MORE
-
23. As Good as it Sounds? The Regularization and Economic Integration of Venezuelan Migrants in Colombia
University essay from Lunds universitet/Graduate SchoolAbstract : The regularization of forcibly displaced migrants is promoted by NGOs and intergovernmental organizations as a good practice in migration policy. Regularization of forcibly displaced migrants increases their protection, facilitates their access to necessary services, increases their resiliency, and provides access to the formal labor market. READ MORE
-
24. Investigation of Facial Age Estimation using Deep Learning
University essay from Uppsala universitet/Institutionen för informationsteknologiAbstract : Age estimation from facial images has drawn increasing attention in the past fewyears. This thesis project performs the age group classification of facial imagesacquired in in-the-wild conditions using deep convolutional neural networkstechniques. READ MORE
-
25. Volatility Forecasting with Artificial Neural Networks: Can we trust them?
University essay from Stockholms universitet/FinansieringAbstract : This thesis investigates how two types of artificial neural network models (ANN), feedforwardneural networks (FNN) and long short-term memory (LSTM), used for realized volatility (RV) forecasting, perform during high and low volatility regimes in comparison to the heterogeneousautoregressive (HAR) model. This is done for 23 stocks, constituents of the Swedish index OMXS30, between the 8th of February 2010 and the 31st of January 2022 using ten exogenous and three endogenous input variables. READ MORE