A Method to Solve overflow or underflow errors Resulting from Activation functions in Convolutional Neural Networks

In this paper, a method is proposed to correct overflow errors of resulting values that can occur when the cross-entropy loss function is used as a softmax and ReLU as an activation function of the convolutional neural network. Since conventional softmax and cross-entropy functions include exponenti...

Celý popis

Podrobná bibliografia

Vydané v:	International Information Institute (Tokyo). Information Ročník 20; číslo 11; s. 8151 - 8158
Hlavní autori:	Jeong, JunMo, Choi, SeJin, Kim, ChiYong
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	Koganei International Information Institute 01.11.2017
Predmet:	Activation Algorithms Artificial neural networks Classification Divergence Entropy Error correction Methods Neural networks Neurons
ISSN:	1343-4500, 1344-8994
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!