Sökning: "Magnus Tornstad"

Hittade 1 uppsats innehållade orden Magnus Tornstad.

  1. 1. Evaluating the Practicality of Using a Kronecker-Factored Approximate Curvature Matrix in Newton's Method for Optimization in Neural Networks

    Kandidat-uppsats, KTH/Skolan för teknikvetenskap (SCI)

    Författare :Magnus Tornstad; [2020]
    Nyckelord :;

    Sammanfattning : For a long time, second-order optimization methods have been regarded as computationally inefficient and intractable for solving the optimization problem associated with deep learning. However, proposed in recent research is an adaptation of Newton's method for optimization in which the Hessian is approximated by a Kronecker-factored approximate curvature matrix, known as KFAC. LÄS MER