Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 667 for “"Online Learning"”.
-
Online Learning in Control Theory
… to achieve a sublinear regret, similar to the online optimization setting. A modified online Riccati algorithm is introduced that under some uniform boundedness assumptions results in a logarithmic regret bound. In particular, the logarithmic regret for the scalar case is achieved without any …
-
DISTRIBUTED AND DELAYED ONLINE LEARNING
… design and analysis of distributed and delayed online learning algorithms. First, we introduce delayed online learning, where model updates rely on feedback arriving with variable delays. We study the online learning problem with curved losses and delayed feedback, designing algorithms that …
-
ONLINE LEARNING METHODS FOR DIGITAL MARKETS
… from digital markets and economics into an online learning framework, where a learner sequentially interacts with an unknown environment, trying to discover its relevant features to maximize her cumulative reward. After an introduction to online learning in Chapter 1, we start with a study …
-
ONLINE LEARNING WITH BANDITS FOR COVERAGE
… this work, we formulate this problem as the {\it online set coverage problem} and propose its solution for recommendation systems and the patrol assignment problem.</p> <p>We propose a novel online reinforcement learning algorithm inspired by the Multi-Armed Bandit problem to solve the online …
-
Leveraging Structured Feedback in Online Learning
L'abstract è presente nell'allegato / the abstract is in the attachment
-
Online learning of non-stationary sequences
Thesis (S.M.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2003.
-
Smoothed Online Learning: Theory and Applications
… theoretical results surrounding modern machine learning are predicated on the assumption that data are independent and identically distributed. Motivated by the numerous applications that do not satisfy this assumption, many researchers have been interested in relaxations of this condition, with …
-
Design and Implementation of Online Learning Environments
… approach in the design and implementation of online learning environments. This approach incorporates the principles of human learning as well as the best practices in software engineering. This thesis implements a conceptual model for the design, and it describes how software elements can be …
-
Group Collaboration in Global Online Learning Environments
This case study seeks to better understand online collaboration in a global secondary school classroom context. Given the widespread promotion of collaborative learning as a crucial skill, coupled with a significant increase in online learning, this study aims to grow research evidence and offer …
-
Culture and Motivation in Online Learning Environments
In the past, instructional design of online learning has largely ignored culture in the creation of online learning environments. Because research in the interaction of culture and online learning is very sparse, an exploratory, blended study was conducted to assess whether there is evidence that …
-
Humanisation of Online Learning: Experiences That Matter.
… humanness and goodness in teaching and learning) is central to education. In modern times, when technology is reshaping our world, addressing humanness is especially important as we face crucial decisions regarding the quo Vadis of education and society. This study explored the …
-
An online learning algorithm for technical trading
We use an adversarial expert based online learning algorithm to learn the optimal parameters required to maximise wealth trading zero-cost portfolio strategies. The learning algorithm is used to determine the relative population dynamics of technical trading strategies that can survive historical …
-
A knowledge services roadmay for online learning
… without any administration-enforced policies. Learning environments are also typically characterized by challenges such as barriers to use, quality control and relevance issues, or issues of credibility of information. These issues are effectively tackled by weblog services since weblogs are …
-
Distributed Online Learning in Cognitive Radar Networks
… into networks. This work first examines the online learning techniques available to distributed CRNs, enabling optimal resource allocation without requiring a dedicated communication resource. While this problem has been addressed for single-node cognitive radar, we provide the first …
-
Structured Online Learning with Full and Bandit Information
… treatments, autonomous robot exploration, online advertising, and algorithmic trading. In such applications, users often have high expectations of the algorithm such as immediately showing relevant recommendations, quickly administering effective treatments, or performing profitable trades …
-
Evolving ontologies with online learning and forgetting algorithms
… specifically, we present three online evolution algorithms that enable agents to: i) augment domain related concepts, ii) use prediction to select concepts to learn, and iii) prune unnecessary concepts from their ontology, with the aim to reduce the costs associated with the …
-
ONLINE LEARNING AND ITS APPLICATIONS IN ELECTRICITY MARKETS
Online learning is the process of learning to make accurate predictions and optimize actions sequentially in each period based on the information gained through the previous decisions and observations. In many real-world problems, the underlying model is unknown and possibly stochastic. Therefore, …
-
Analyzing Student Readiness for Online Learning in Higher Education
… seeks to investigate students’ readiness in an online learning environment and examine how well Royal Roads University’s (RRU) pedagogical model aligns with their intended educational outcomes. By providing an anonymous platform for students to share their perspectives, the study addresses the …
Page 1 of 34