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 162 for “"optimal learning"”.
-
Optimal Learning Theory and Approximate Optimal Learning Algorithms
… intractable problem in reinforcement learning. The dilemma also impacts data efficiency which can be pivotal when the interactions between the agent and the environment are constrained. Traditional optimal control theory has some notion of objective criterion, such as regret, …
-
Optimal Learning with Conditional Guarantees
… and computationally efficient algorithms for learning predictors with provable conditional calibration guarantees. These frameworks apply even in online adversarial settings, where data arrive sequentially and may be adversarially generated. On the sample-complexity side, we obtain minimax …
-
Optimal Learning with Non-Gaussian Rewards
… the author studies sequential Bayesian learning problems modeled under non-Gaussian distributions. We focus on a class of problems called the multi-armed bandit problem, and studies its optimal learning strategy, the Gittins index policy. The Gittins index is computationally intractable …
-
Optimal Learning Rates for Neural Networks
… and sensitivity to hyperparameters such as learning rate and architecture. Hyperparameter searches are notorious for requiring tremendous amounts of processing power and human resources. This thesis provides an analytic approach to estimating the optimal value of one of the key …
-
Optimal information disclosure and optimal learning
… The first chapter examines the design of an optimal feedback mechanism by an informed principal and uses the results to explain why firms tend to assign coarse subjective ratings to their employees. When a firm has private information about an employee's ability, it can communicate this …
-
STATISTICAL AND OPTIMAL LEARNING WITH APPLICATIONS IN BUSINESS ANALYTICS
Statistical learning is widely used in business analytics to discover structure or exploit patterns from historical data, and build models that capture relationships between an outcome of interest and a set of variables. Optimal learning on the other hand, solves the operational side of the …
-
Affect and achievement: creating an optimal learning experience in mathematics
… student engagement and motivation: problem-based learning, mastery learning, and student self-assessment. We consider each of these instructional methods in turn as ways to enhance student self-efficacy and positive affect and conduct a statistical analysis on the correlations between these …
-
Efficient Computational Design and Analysis via Distribution-Based Optimal Learning
… leverages probabilistic transformations, optimal assignment algorithms, and Sobol' (t, m, s)-nets to reorder existing samples into nested batches of increasing size, enabling the early delivery of high-confidence estimates well before the entire set of samples is processed. Numerical …
-
Efficient Computational Design and Analysis via Distribution-Based Optimal Learning
… leverages probabilistic transformations, optimal assignment algorithms, and Sobol' (t, m, s)-nets to reorder existing samples into nested batches of increasing size, enabling the early delivery of high-confidence estimates well before the entire set of samples is processed. Numerical …
-
Efficient Computational Design and Analysis via Distribution-Based Optimal Learning
… leverages probabilistic transformations, optimal assignment algorithms, and Sobol' (t, m, s)-nets to reorder existing samples into nested batches of increasing size, enabling the early delivery of high-confidence estimates well before the entire set of samples is processed. Numerical …
-
Efficient Computational Design and Analysis via Distribution-Based Optimal Learning
… leverages probabilistic transformations, optimal assignment algorithms, and Sobol' (t, m, s)-nets to reorder existing samples into nested batches of increasing size, enabling the early delivery of high-confidence estimates well before the entire set of samples is processed. Numerical …
-
Optimal learning of deployment and search strategies for robotic teams
In the problem of optimal learning, the dilemma of exploration and exploitation stems from the fact that gathering information and exploiting it are, in many cases, two mutually exclusive activities. The key to optimal learning is to strike a balance between exploration and exploitation. The …
-
OPTIMAL LEARNING FROM INCOMPLETE OBSERVATIONS: THEORY AND APPLICATIONS IN STELLAR SPECTROSCOPY
This dissertation studies inverse problems in which a physical or statistical quantity must be inferred from incomplete observations, with stellar spectroscopy as the main scientific setting. Its central contribution is a specified-experiment error ledger: after fixing a prior, an observation …
-
CREATING OPTIMAL LEARNING ENVIRONMENTS BY INTEGRATING INSTRUCTIONAL METHODS, ASSESSMENT, AND CLASSROOM MANAGEMENT
A portfolio submitted in partial fulfillment of the requirements for the degree of Master of Education in Special Education in the Department of Special Education in the Bagwell College of Education of Kennesaw State University
-
The Influence of Authentic Leadership in Creating Conditions for Optimal Learning: A Hermeneutic Phenomenological Study
Learning is an evolution of thought grounded in the experiences, complexities, and fluidity of life. Embedded in optimizing that journey toward understanding is availing oneself of the introspective practices that foster self-awareness as a means to contribute, advance, and inspire the greater good …
-
Modeling olfactory processing and insights on optimal learning in constrained neural networks: learning from the anatomy of the Drosophila mushroom body.
… at the same time. Ideally, they will reach an optimal state of equilibrium where the outcome from any goal cannot get better without at the same time making another worse off, similar to the state of Pareto optimaility (Mock 2011). Animals can seek different goals like, to maintain their …
-
Data-driven adaptive learning systems
"Adaptive learning systems are capable of providing more adaptive and efficient assessment and learning experiences for learners than traditional classroom settings. A conventional adaptive learning system involves a learner, a latent trait estimator, and a learning strategy/plan. The latent trait …
-
APPLICATION OF COGNITIVE PRINCIPLES WITHIN AN ONLINE STATISTICAL LEARNING ENVIRONMENT
… were conducted in order to further investigate optimal learning procedures within an online statistical learning environment. Experiment 1 exposed learners to retrieval practice learning conditions with or without segmentation. Retrieval practice formats included; multiple choice, open ended, …
-
The Processes of Collective Buy-In, Actuation, and Deep Social Learning in Seminary Classes
… seminary teachers in a Western state. CCA is an optimal learning state of a class collective. Data were gathered through interviews, observations, and a focus group. Data analysis yielded themes, textural and structural descriptions, an overall essence, and a model explaining the processes of …
-
Gebėjimų nerealizuojančių paauglių mokymosi patyrimas /
… study was aimed at revealing the subjective learning experiences of adolescents who underachieve in academic performance. In the first part of the study, nine participants were selected to participate in the study. They were selected from 107 students who studied at five schools in four areas …
Page 1 of 9