Sökning: "KTH matematisk statistik"
Visar resultat 1 - 5 av 35 avhandlingar innehållade orden KTH matematisk statistik.
1. Models for Additive and Sufficient Cause Interaction
Sammanfattning : The aim of this thesis is to develop and explore models in, and related to, the sufficient cause framework, and additive interaction. Additive interaction is closely connected with public health interventions and can be used to make inferences about the sufficient causes in order to find the mechanisms behind an outcome, for instance a disease. LÄS MER
2. Topics on Large Deviations in Artificial Intelligence
Sammanfattning : Artificial intelligence has become one of the most important fields of study during the last decade. Applications include medical sciences, autonomous vehicles, finance and everyday life. Therefore the analysis of convergence and stability of these algorithms is of utmost importance. LÄS MER
3. Data driven modeling in the presence of time series structure: : Improved bounds and effective algorithms
Sammanfattning : This thesis consists of five appended papers devoted to modeling tasks where the desired models are learned from data sets with an underlying time series structure. We develop a statistical methodology for providing efficient estimators and analyzing their non-asymptotic behavior. LÄS MER
4. Probabilistic machine learning methods for automated radiation therapy treatment planning
Sammanfattning : In this thesis, different parts of an automated process for radiation therapy treatment planning are investigated from a mathematical and computational perspective. Whereas traditional inverse planning is labor-intensive, often comprising several reiterations between treatment planner and physician before a plan can be approved, much of recent research have been aimed at using a data-driven approach by learning from historically delivered plans. LÄS MER
5. Markov Chain Monte Carlo Methods and Applications in Neuroscience
Sammanfattning : An important task in brain modeling is that of estimating model parameters and quantifying their uncertainty. In this thesis we tackle this problem from a Bayesian perspective: we use experimental data to update the prior information about model parameters, in order to obtain their posterior distribution. LÄS MER