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 514 for “"learning problem"”.

  1. Smoothening Functions and the Homomorphism Learning Problem

    … certain algebraic and geometrical aspects of the Learning With Errors (LWE) problem introduced in Reg05. On the algebraic front, we view it as a Learning Homomorphisms with Noise problem, and provide a generic construction of a public-key cryptosystem based on this generalization. On the geometric …

    waterloo Repository record for Smoothening Functions and the Homomorphism Learning Problem (opens in a new tab)

  2. Experts learning : problem solving in a simulated environment

    … an expert can learn new ways for solving problems in his domain of expertise. The simulated environment used for this study consisted of both an expert system and hypertext program. The method employed in this research was qualitative and was largely dependent on the phenomenological …

    utk-theses Repository record for Experts learning : problem solving in a simulated environment (opens in a new tab)

  3. Experimental Investigation of Quasi-Newton Approaches to a Learning Problem in Electronic Negotiation

    … an examination of optimization approaches for learning the parameters of a time-dependent decision-function that has recently obtained significant interest in the negotiation literature. Twelve different nonlinear optimization variants are evaluated using 800 problems, and the resulting 9600 …

    waterloo Repository record for Experimental Investigation of Quasi-Newton Approaches to a Learning Problem in Electronic Negotiation (opens in a new tab)

  4. The effect of learning problem-solving methods on learning to program in the BASIC language

    <p>This study was designed to compare learning problem-solving methods versus non problem-solving activity (word-processing) on subsequent learning to program in the BASIC language. It also examined a method to provide students with increased knowledge and skills to enable them to learn how to …

    iastate Repository record for The effect of learning problem-solving methods on learning to program in the BASIC language (opens in a new tab)

  5. Nonparametric regression estimation with applications in radial basis networks and learning

    This study explores the learning problem from two broad perspectives, consisting of statistical regression estimation and RBF network formulation.

    concordia Download PDF for Nonparametric regression estimation with applications in radial basis networks and learning (opens in a new tab)

  6. Optimal chaos control through reinforcement learning

    … of chaotic systems based on reinforcement learning. Reinforcement learning algorithms provide a solution to the optimal control of systems in situations where system dynamics and analytic information about the desired goal state are not available. We formulate the chaos control problem as a …

    colostate Repository record for Optimal chaos control through reinforcement learning (opens in a new tab)

  7. Concept Learning By Example Decomposition

    … we rely on different ways of simplifying the learning problem. One simplifying technique that is highly pervasive in nature is to break down a large learning problem into smaller ones; to learn the smaller, more manageable problems; and then to recombine them to obtain the larger picture. It …

    ucf Repository record for Concept Learning By Example Decomposition (opens in a new tab)

  8. Random forest for dissimilarity based multi-view learning : application to radiomics

    … work of this thesis was initiated by a Radiomic learning problem. Radiomics is a medical discipline that aims at the large-scale analysis of data from traditional medical imaging to assist in the diagnosis and treatment of cancer. The main hypothesis of this discipline is that by extracting a …

    ets-quebec Download PDF for Random forest for dissimilarity based multi-view learning : application to radiomics (opens in a new tab)

  9. Deep reinforcement learning approaches for process control

    … processing that followed the success of deep learning. Human level control has been attained in games and physical tasks by combining deep learning with reinforcement learning. They were also able to learn the complex go game which has states more than number of atoms in the universe. …

    ubc Repository record for Deep reinforcement learning approaches for process control (opens in a new tab) Download PDF for Deep reinforcement learning approaches for process control (opens in a new tab)

  10. Collaborative learning for recommender systems by boosting and non-parametric methods

    … the task of recommendation as a collaborative learning problem and proposes a novel method named gradient weighted matrix factorisation that incorporates user-item importance weight while learn to solve the collaborative learning problem for matrix factorisation. The research proposes a method …

    unsw Repository record for Collaborative learning for recommender systems by boosting and non-parametric methods (opens in a new tab)

  11. A Rate of Convergence for Learning Theory with Consensus

    This thesis poses and solves a distribution free learning problem with consensus that arises in the study of estimation and control strategies for distributed sensor networks. Each node i for i = 1, . . . , n of the sensor network collects independent and identically distributed local measurements …

    vt Repository record for A Rate of Convergence for Learning Theory with Consensus (opens in a new tab)

  12. Data-Efficient Learning of Semantic Segmentation

    Semantic segmentation is a fundamental problem in visual perception with a wide range of applications ranging from robotics to autonomous vehicles, and recent approaches based on deep learning have achieved excellent performance. However, to train such systems there is in general a need for very …

    lund Repository record for Data-Efficient Learning of Semantic Segmentation (opens in a new tab) Download PDF for Data-Efficient Learning of Semantic Segmentation (opens in a new tab)

  13. A review on constrained recurrent sparse auto-encoder

    Sparse Dictionary Learning generates a sparse representation for images and signals along with a generalized learned dictionary. We examine closely to the constrained recurrent sparse auto-encoder (CRsAE) on its Encoder-Decoder plus recurrent architecture and experimenting CRsAE’s position in the …

    texas Repository record for A review on constrained recurrent sparse auto-encoder (opens in a new tab)

  14. An Evaluation of the Automated Reading Program: First Steps in Reading for Meaning

    … indicated need for a method that deals with the learning problem of each individual non-reading student. The TMI-Grollier Self-Tutoring Program, "First Steps In Reading for Meaning" offers the possibility of a solution to the problem of how to individualize instruction. The purpose of this study …

    central-wash Repository record for An Evaluation of the Automated Reading Program: First Steps in Reading for Meaning (opens in a new tab)

  15. Unsupervised Learning for Face Anti-Spoofing Models

    … automatic authentication. The anomaly detection problem in high dimensional data such as images can be addressed as a supervised or unsupervised learning problem, but when spoof data is sparse and not all spoof domains can be represented in training the unsupervised model can generalize knowledge …

    chalmers Repository record for Unsupervised Learning for Face Anti-Spoofing Models (opens in a new tab)

  16. Aprendizagem semissupervisionada por meio de técnicas de Deep Learning e de Teoria da Informação

    … about labels, has made semi-supervised learning one of the problems of practical importance in modern data analysis. In most cases, obtaining a dataset with enough examples to induce a classifier can be costly, as it is necessary to perform labeling of the data by an expert. Unlabeled …

    brazil-ufrn Repository record for Aprendizagem semissupervisionada por meio de técnicas de Deep Learning e de Teoria da Informação (opens in a new tab)

  17. Robust and fair learning: From correlation matrices to fair learning models

    … of convex optimisations to address two types of problems. In the first chapter, we review the nearest correlation matrix problem, a problem in actuarial science and finance, to find the nearest correlation matrix that is positive semidefinite. We introduce two algorithms to solve the problem, …

    city-london Download PDF for Robust and fair learning: From correlation matrices to fair learning models (opens in a new tab)

  18. Traumatic Brain Injury in Adolescence: The Relationship between High School Exiting and Future Productivity

    … White, not receiving Medicaid, no pre-injury learning problem, no pre-injury learning problem, injury severity, higher motor functioning at rehabilitation discharge, acute length of stay) and others with GED (i.e., pre-injury learning problem, pre-injury substance use problem) or dropout …

    usf Repository record for Traumatic Brain Injury in Adolescence: The Relationship between High School Exiting and Future Productivity (opens in a new tab)

Page 1 of 26