A target oriented averaging search trajectory and its application in artificial neural networks

A target oriented averaging search trajectory and its application in artificial neural networks

The training of artificial neural networks usually involves nonsmooth objective func- tions to be minimized. This optimization problem is currently solved just avoing saddle points and thus reaching a local and fortunately a global minimizer. Well-known opti- mizers like Gradient Descent (GD) or its...

Cijeli opis

Spremljeno u:
Bibliografski detalji
Glavni autor: Rojas Jiménez, Ángel Adrián (author)
Format: bachelorThesis
Jezik:eng
Izdano: 2019
Teme:
Successive Abs-Linearization
Quadratic Regularization
AbsNormal Form
Generalized descent
Dynamic Search Trajectory
Abs-Linearización Sucesiva
Regularización Cuadrática
Forma Abs-Normal
Descenso Generalizado
Trayectoria de búsqueda dinámica
Online pristup:http://repositorio.yachaytech.edu.ec/handle/123456789/104
Oznake: Dodaj oznaku
Bez oznaka, Budi prvi tko označuje ovaj zapis!

Internet

http://repositorio.yachaytech.edu.ec/handle/123456789/104

Slični predmeti