Sökning: "bounded learning theory."
Visar resultat 1 - 5 av 11 avhandlingar innehållade orden bounded learning theory..
1. War and Unreason. Bounded Learning Theory and War Duration
Sammanfattning : Why are some wars longer than others? Offense-defense theorists have assumed that wars are shorter and it is more difficult for states to create security when military technology favors the offense and attacking is easier than defending. This study argues that this assumption is wrong on both accounts. LÄS MER
2. Statistical Learning, Dynamics and Control : Fast Rates and Fundamental Limits for Square Loss
Sammanfattning : Learning algorithms play an ever increasing role in modern engineering solutions. However, despite many recent successes, their performance in the context of dynamical and control systems is not exactly well-understood. LÄS MER
3. Crisis-induced learning in public sector organizations
Sammanfattning : How do public organizations manage crises? How do public organizations learnfrom crises? These seemingly basic questions still pose virtual puzzles for crisismanagement researchers. Yet, the interest of the academic and practitionerrealms in crisis management has grown in recent years. LÄS MER
4. Computational Modeling of Cancer Progression
Sammanfattning : Cancer is a multi-stage process resulting from accumulation of genetic mutations. Data obtained from assaying a tumor only contains the set of mutations in the tumor and lacks information about their temporal order. Learning the chronological order of the genetic mutations is an important step towards understanding the disease. LÄS MER
5. An Information-Theoretic Approach to Generalization Theory
Sammanfattning : In this thesis, we investigate the in-distribution generalization of machine learning algorithms, focusing on establishing rigorous upper bounds on the generalization error. We depart from traditional complexity-based approaches by introducing and analyzing information-theoretic bounds that quantify the dependence between a learning algorithm and the training data. LÄS MER