Deep Neural Networks in a Mathematical Framework (Paperback)

Dong Eui Chang

ISBN 10: 3319753037 / ISBN 13: 9783319753034

Published by Springer International Publishing AG, Cham, 2018

About this Item

Paperback. This SpringerBrief describes how to build a rigorous end-to-end mathematical framework for deep neural networks. The authors provide tools to represent and describe neural networks, casting previous results in the field in a more natural light. 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. Furthermore, the authors developed framework is both more concise and mathematically intuitive than previous representations of neural networks.This SpringerBrief is one step towards unlocking the black box of Deep Learning. The authors believe that this framework will help catalyze further discoveries regarding the mathematical properties of neural networks.This SpringerBrief is accessible not only to researchers, professionals and students working and studying in the field of deep learning, but alsoto those outside of the neutral network community. 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. Shipping may be from multiple locations in the US or from the UK, depending on stock availability.

Seller Inventory # 9783319753034

Bibliographic Details

• Title: Deep Neural Networks in a Mathematical Framework (Paperback)
• Publisher: Springer International Publishing AG, Cham
• Publication Date: 2018
• Language: English
• ISBN 10: 3319753037
• ISBN 13: 9783319753034
• Binding: Paperback
• Edition: 1st Edition
• Condition: new

About this title

Synopsis

This SpringerBrief describes how to build a rigorous end-to-end mathematical framework for deep neural networks. The authors provide tools to represent and describe neural networks, casting previous results in the field in a more natural light. 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. Furthermore, the authors developed framework is both more concise and mathematically intuitive than previous representations of neural networks.

This SpringerBrief is one step towards unlocking the black box of Deep Learning. The authors believe that this framework will help catalyze further discoveries regarding the mathematical properties of neural networks.This SpringerBrief is accessible not only to researchers, professionals and students working and studying in the field of deep learning, but alsoto those outside of the neutral network community.