Algoritmi za brzo aproksimativno spektralno učenje
Докторанд
Trokicić, Aleksandar B.Ментор
Todorović, BranimirЧланови комисије
Ćirić, Miroslav
Ognjanović, Zoran
Janković, Dragan
Petković, Marko
Метаподаци
Приказ свих података о дисертацијиСажетак
This thesis presents learning algorithms which use the
information stored in the spectrum (eigenvalues and
eigenvectors) of a matrix derived from the input set. Matrices
in question are graph matrices or kernel matrices. However, the
algorithms which use these matrices have either a quadratic or
cubic time complexity and quadratic memory complexity.
Therefore, in this thesis the algorithms will be presented that
approximate those matrices and reduce the time and memory
complexity to the linear one. Also, these algorithms will be
compared with the other algorithms that solve this problem, and
their empirical and theoretical analysis will be presented.