Particle Filters and Markov Chains for Learning of Dynamical Systems.

• Superior document: Linköping Studies in Science and Technology. Dissertations Series ; v.1530
• Author: Lindsten, Fredrik.
• Place / Publishing House: Linköping : : Linkopings Universitet,, 2013.; {copy}2013.
• Year of Publication: 2013
• Edition: 1st ed.
• Language: English
• Series: Linköping Studies in Science and Technology. Dissertations Series
• Physical Description: 1 online resource (65 pages)

Table of Contents

Intro -- Abstract -- Populärvetenskaplig sammanfattning -- Acknowledgments -- Contents -- Notation -- I Background -- 1 Introduction -- 1.1 Models of dynamical systems -- 1.2 Inference and learning -- 1.3 Contributions -- 1.4 Publications -- 1.5 Thesis outline -- 1.5.1 Outline of Part I -- 1.5.2 Outline of Part II -- 2 Learning of dynamical systems -- 2.1 Modeling -- 2.2 Maximum likelihood -- 2.3 Bayesian learning -- 2.4 Data augmentation -- 2.5 Online learning -- 3 Monte Carlo methods -- 3.1 The Monte Carlo idea -- 3.2 Rejection Sampling -- 3.3 Importance sampling -- 3.4 Particle filters and Markov chains -- 3.5 Rao-Blackwellization -- 4 Concluding remarks -- 4.1 Conclusions and future work -- 4.2 Further reading -- Bibliography.