Deep neural networks in a mathematical framework
Auteur :
Caterini, Anthony L. / Chang, Dong Eui
Éditeur :
Springer International Publishing AG
ISBN :
9783319753034
Date de publication :
3 avr. 2018
Dimensions :
23,5 x 15,5 cm
Langue :
Anglais
Pays d'origine :
Suisse
This SpringerBrief describes how to build a rigorous end-to-end mathematical framework for deep neural networks. In particular, the authors derive gradient descent algorithms in a unified way for several neural network structures, including multilayer perceptrons, convolutional neural networks, deep autoencoders and recurrent neural networks.