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 503 for “"regularization"”.
-
REGULARIZATION ON MACHINE LEARNING
… occurs. To achieve better generalization, many regularization methods were proposed to reduce overfitting. In this thesis, we propose a simple-yet-effective regularization method called Drop-Activation. At the training phase, we drop nonlinear activation functions randomly and set them to be …
-
fMRI detection with spatial regularization
… the major drawback of the conventional spatial regularization models such as the Gaussian smoothing model.
-
Explicit Regularization for Overparameterized Models
… it is desirable to incorporate explicit regularization in the objective to avoid overfitting the data. Typically, the regularized objective is solved via weight decay. However, optimizing with weight decay can be challenging because we cannot tell if the solution has reached a global …
-
Higher-Order Regularization in Computer Vision
… To reduce ambiguity and noise in the solution, regularization terms are included into the objective function, enforcing different properties of the solution. The most commonly used regularization is penalization of boundary length, which requires a second-order objective function. Most of this …
-
REGULARIZATION METHODS FOR ILL-POSED POISSON IMAGING
… function is ill-posed, and hence some form of regularization is required. In this work, it involves solving a variational problem of the form u def = arg min u0 `(Au; z) + J(u); where ` is the negative-log of a Poisson likelihood functional, and J is a regularization functional. The main result …
-
REGULARIZATION METHODS FOR ILL-POSED POISSON IMAGING
… function is ill-posed, and hence some form of regularization is required. In this work, it involves solving a variational problem of the form u def = arg min u0 `(Au; z) + J(u); where ` is the negative-log of a Poisson likelihood functional, and J is a regularization functional. The main result …
-
Adversarial graph contrastive learning with information regularization
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2022-11-11 without embargo terms
-
Regularization for dysarthric speech recognition and telemedicine applications
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2022-11-11 without embargo terms
-
The information regularization framework for semi-supervised learning
… This thesis is a study of the information regularization method for semi-supervised classification, a unified framework that encompasses many of the common approaches to semi-supervised learning, including parametric models of incomplete data, harmonic graph regularization, redundancy of …
-
Results of true-anomaly regularization in orbital mechanics
… are some analytical results available from regularization of the differential equations of satellite motion. True-anomaly regularization is developed as a special case of a more general Sundman-type transformation of the independent variable (time) in the equations of motion. Constants of …
-
Regularization based multitask learning with applications in computational biology
Diese Arbeit befasst sich mit einem in der biologischen Forschung alltäglichen Problem: Dem Entschlüsseln von biologischen Prozessen mit Hilfe von Experimenten aus verschiedenen biologischen Einheiten. So kann z.B. das Wissen aus verschiedenen Organismen, Gewebetypen, oder Tumorarten jeweils …
-
Resource Management for Distributed Estimation via Sparsity-Promoting Regularization
<p>Recent advances in wireless communications and electronics have enabled the development of low-cost, low-power, multifunctional sensor nodes that are small in size and communicate untethered in a sensor network. These sensor nodes can sense, measure, and gather information from the environment …
-
The role of explicit regularization in overparameterized neural networks
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2022-04-06 without embargo terms
-
A regularization framework for active learning from imbalanced data
… and facilitates the automatic selection of a regularization parameter through exact and efficient calculation of the Leave One Out error. Next, we present two methods that estimate multiclass confidence from an asymptotic analysis of RLS and another method that stems from a Bayesian …
-
Functional Norm Regularization for Margin-Based Ranking on Temporal Data
… dissertation is that use of the functional norm regularization can help alleviating mentioned challenges, by improving generalization abilities and/or learning efficiency of predictive models, in this case specifically of the approaches based on the ranking SVM framework. The temporal nature of …
Page 1 of 26