Cover Image

Deep Neural Networks in a Mathematical Framework

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 algo...

Full description

Main Authors: Caterini, Anthony L. (Author, http://id.loc.gov/vocabulary/relators/aut), Chang, Dong Eui. (http://id.loc.gov/vocabulary/relators/aut)
Corporate Author: SpringerLink (Online service)
Language:English
Published: Cham : Springer International Publishing : Imprint: Springer, 2018.
Edition:1st ed. 2018.
Series:SpringerBriefs in Computer Science,
Subjects:
Artificial intelligence.
Pattern recognition.
Artificial Intelligence.
Pattern Recognition.
Online Access:https://doi.org/10.1007/978-3-319-75304-1
LEADER 02968nam a22004815i 4500
001 978-3-319-75304-1
003 DE-He213
005 20200705125455.0
007 cr nn 008mamaa
008 180322s2018 gw | s |||| 0|eng d
020 |a 9783319753041  |9 978-3-319-75304-1 
024 7 |a 10.1007/978-3-319-75304-1  |2 doi 
050 4 |a Q334-342 
072 7 |a UYQ  |2 bicssc 
072 7 |a COM004000  |2 bisacsh 
072 7 |a UYQ  |2 thema 
082 0 4 |a 006.3  |2 23 
100 1 |a Caterini, Anthony L.  |e author.  |4 aut  |4 http://id.loc.gov/vocabulary/relators/aut 
245 1 0 |a Deep Neural Networks in a Mathematical Framework  |h [electronic resource] /  |c by Anthony L. Caterini, Dong Eui Chang. 
250 |a 1st ed. 2018. 
264 1 |a Cham :  |b Springer International Publishing :  |b Imprint: Springer,  |c 2018. 
300 |a XIII, 84 p.  |b online resource. 
336 |a text  |b txt  |2 rdacontent 
337 |a computer  |b c  |2 rdamedia 
338 |a online resource  |b cr  |2 rdacarrier 
347 |a text file  |b PDF  |2 rda 
490 1 |a SpringerBriefs in Computer Science,  |x 2191-5768 
520 |a 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 also to those outside of the neutral network community. 
650 0 |a Artificial intelligence. 
650 0 |a Pattern recognition. 
650 1 4 |a Artificial Intelligence.  |0 https://scigraph.springernature.com/ontologies/product-market-codes/I21000 
650 2 4 |a Pattern Recognition.  |0 https://scigraph.springernature.com/ontologies/product-market-codes/I2203X 
700 1 |a Chang, Dong Eui.  |e author.  |4 aut  |4 http://id.loc.gov/vocabulary/relators/aut 
710 2 |a SpringerLink (Online service) 
773 0 |t Springer Nature eBook 
776 0 8 |i Printed edition:  |z 9783319753034 
776 0 8 |i Printed edition:  |z 9783319753058 
830 0 |a SpringerBriefs in Computer Science,  |x 2191-5768 
856 4 0 |u https://doi.org/10.1007/978-3-319-75304-1 
912 |a ZDB-2-SCS 
912 |a ZDB-2-SXCS 
950 |a Computer Science (SpringerNature-11645) 
950 |a Computer Science (R0) (SpringerNature-43710) 

Similar Items