Sökning: "Gradient descent method"

Visar resultat 6 - 10 av 17 avhandlingar innehållade orden Gradient descent method.

  1. 6. Variational Problems and Level Set Methods in Computer Vision - Theory and Applications

    Författare :Jan Erik Solem; Matematik LTH; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Mathematics; level set methods; computer vision; variational problems; Matematik;

    Sammanfattning : Current state of the art suggests the use of variational formulations for solving a variety of computer vision problems. This thesis deals with such variational problems which often include the optimization of curves and surfaces. LÄS MER

  3. 7. Collaborative Predictive Maintenance for Smart Manufacturing : From Wireless Control to Federated Learning

    Författare :Ali Bemani; Niclas Björsell; Janet Lin; Högskolan i Gävle; []
    Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY;

    Sammanfattning : Industry 4.0 represents a significant shift in the industrial landscape, aimed at improving efficiency, productivity, and competitiveness. This shift involves the digitalization of industries, impacting manufacturing and maintenance processes. LÄS MER

  4. 8. Module identification in dynamic networks: parametric and empirical Bayes methods

    Författare :Niklas Everitt; Håkan Hjalmarsson; Cristian R. Rojas; Paul Van den Hof; KTH; []
    Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Electrical Engineering; Elektro- och systemteknik;

    Sammanfattning : The purpose of system identification is to construct mathematical models of dynamical system from experimental data. With the current trend of dynamical systems encountered in engineering growing ever more complex, an important task is to efficiently build models of these systems. LÄS MER

  5. 9. Extensions and Applications of Fast-Lipschitz Optimization

    Författare :Martin Jakobsson; Carlo Fischione; Michael Rabbat; KTH; []
    Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY;

    Sammanfattning : Fast-Lipschitz optimization is a framework for optimization problems having a special structure in which the optimal solution is given by a set of equations, easily solvable through fixed point iterations. This solution method is simple to implement and particularly well suited for distributed optimization applications, such as those arising in wireless sensor networks. LÄS MER

  7. 10. Asynchronous First-Order Algorithms for Large-Scale Optimization : Analysis and Implementation

    Författare :Arda Aytekin; Mikael Johansson; Lin Xiao; KTH; []
    Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; convex; optimization; asynchronous; algorithms; parallel; distributed; large-scale; big data; software; serverless; Electrical Engineering; Elektro- och systemteknik;

    Sammanfattning : Developments in communication and data storage technologies have made large-scale data collection more accessible than ever. The transformation of this data into insight or decisions typically involves solving numerical optimization problems. LÄS MER