Výsledky vyhledávání - "Reynard, Matthew"

Report

If dropout limits trainable depth, does critical initialisation still matter? A large-scale statistical analysis on ReLU networks

Autor: Pretorius, Arnu, van Biljon, Elan, van Niekerk, Benjamin, Eloff, Ryan, Reynard, Matthew, James, Steve, Rosman, Benjamin, Kamper, Herman, Kroon, Steve

Recent work in signal propagation theory has shown that dropout limits the depth to which information can propagate through a neural network. In this paper, we investigate the effect of initialisation on training speed and generalisation for ReLU net

Externí odkaz: http://arxiv.org/abs/1910.05725

Zobrazit plný text záznamu

Akademický článek

If dropout limits trainable depth, does critical initialisation still matter? A large-scale statistical analysis on ReLU networks

Autor: Pretorius, Arnu ^a, van Biljon, Elan ^a, van Niekerk, Benjamin ^b, Eloff, Ryan ^b, Reynard, Matthew ^b, James, Steve ^c, Rosman, Benjamin ^c, Kamper, Herman ^{⁎, b}, Kroon, Steve ^a

Publikováno v: In Pattern Recognition Letters October 2020 138:95-105

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání