國立虎尾科技大學 |

Deep Belief Nets in C++ and CUDA C.. Volume 1,. Restricted Boltzmann machines and supervised feedforward networks

Record Type:	Language materials, printed : Monograph/item
Title/Author:	Deep Belief Nets in C++ and CUDA C./ by Timothy Masters.
remainder title:	Restricted Boltzmann machines and supervised feedforward networks
Author:	Masters, Timothy.
Published:	Berkeley, CA :Apress : : 2018.,
Description:	ix, 219 p. :ill., digital ; : 24 cm.;
Contained By:	Springer eBooks
Subject:	Neural networks (Computer science) -
Online resource:	http://dx.doi.org/10.1007/978-1-4842-3591-1
ISBN:	9781484235911

Deep Belief Nets in C++ and CUDA C.. Volume 1,. Restricted Boltzmann machines and supervised feedforward networks
Masters, Timothy.

Deep Belief Nets in C++ and CUDA C.Volume 1,Restricted Boltzmann machines and supervised feedforward networks[electronic resource] /Restricted Boltzmann machines and supervised feedforward networksby Timothy Masters. - Berkeley, CA :Apress :2018. - ix, 219 p. :ill., digital ;24 cm.

1. Introduction -- 2. Supervised Feedforward Networks -- 3. Restricted Boltzmann Machines -- 4. Greedy Training: Generative Samplings -- 5. DEEP Operating Manual.

Discover the essential building blocks of the most common forms of deep belief networks. At each step this book provides intuitive motivation, a summary of the most important equations relevant to the topic, and concludes with highly commented code for threaded computation on modern CPUs as well as massive parallel processing on computers with CUDA-capable video display cards. The first of three in a series on C++ and CUDA C deep learning and belief nets, Deep Belief Nets in C++ and CUDA C: Volume 1 shows you how the structure of these elegant models is much closer to that of human brains than traditional neural networks; they have a thought process that is capable of learning abstract concepts built from simpler primitives. As such, you'll see that a typical deep belief net can learn to recognize complex patterns by optimizing millions of parameters, yet this model can still be resistant to overfitting. All the routines and algorithms presented in the book are available in the code download, which also contains some libraries of related routines. You will: Employ deep learning using C++ and CUDA C Work with supervised feedforward networks Implement restricted Boltzmann machines Use generative samplings Discover why these are important.

ISBN: 9781484235911

Standard No.: 10.1007/978-1-4842-3591-1doiSubjects--Topical Terms:

528588
Neural networks (Computer science)

LC Class. No.: QA76.87 / .M368 2018

Dewey Class. No.: 006.32

Deep Belief Nets in C++ and CUDA C.. Volume 1,. Restricted Boltzmann machines and supervised feedforward networks
LDR:02557nam a2200337 a 4500 001 925975
003 DE-He213
005 20180423150045.0
006 m d
007 cr nn 008maaau
008 190625s2018 cau s 0 eng d
020 $a 9781484235911 $q (electronic bk.)
020 $a 9781484235904 $q (paper)
024 7 $a 10.1007/978-1-4842-3591-1 $2 doi
035 $a 978-1-4842-3591-1
040 $a GP $c GP
041 0 $a eng
050 4 $a QA76.87 $b .M368 2018
072 7 $a UMA $2 bicssc
072 7 $a COM014000 $2 bisacsh
072 7 $a COM018000 $2 bisacsh
082 0 4 $a 006.32 $2 23
090 $a QA76.87 $b .M423 2018
100 1 $a Masters, Timothy. $3 1204136
245 1 0 $a Deep Belief Nets in C++ and CUDA C. $n Volume 1, $p Restricted Boltzmann machines and supervised feedforward networks $h [electronic resource] / $c by Timothy Masters.
246 3 0 $a Restricted Boltzmann machines and supervised feedforward networks
260 $a Berkeley, CA : $b Apress : $b Imprint: Apress, $c 2018.
300 $a ix, 219 p. : $b ill., digital ; $c 24 cm.
505 0 $a 1. Introduction -- 2. Supervised Feedforward Networks -- 3. Restricted Boltzmann Machines -- 4. Greedy Training: Generative Samplings -- 5. DEEP Operating Manual.
520 $a Discover the essential building blocks of the most common forms of deep belief networks. At each step this book provides intuitive motivation, a summary of the most important equations relevant to the topic, and concludes with highly commented code for threaded computation on modern CPUs as well as massive parallel processing on computers with CUDA-capable video display cards. The first of three in a series on C++ and CUDA C deep learning and belief nets, Deep Belief Nets in C++ and CUDA C: Volume 1 shows you how the structure of these elegant models is much closer to that of human brains than traditional neural networks; they have a thought process that is capable of learning abstract concepts built from simpler primitives. As such, you'll see that a typical deep belief net can learn to recognize complex patterns by optimizing millions of parameters, yet this model can still be resistant to overfitting. All the routines and algorithms presented in the book are available in the code download, which also contains some libraries of related routines. You will: Employ deep learning using C++ and CUDA C Work with supervised feedforward networks Implement restricted Boltzmann machines Use generative samplings Discover why these are important.
650 0 $a Neural networks (Computer science) $3 528588
650 0 $a C++ (Computer program language) $3 528669
650 1 4 $a Computer Science. $3 593922
650 2 4 $a Computing Methodologies. $3 640210
650 2 4 $a Programming Languages, Compilers, Interpreters. $3 669782
650 2 4 $a Big Data. $3 1017136
650 2 4 $a Big Data/Analytics. $3 1106909
710 2 $a SpringerLink (Online service) $3 593884
773 0 $t Springer eBooks
856 4 0 $u http://dx.doi.org/10.1007/978-1-4842-3591-1
950 $a Professional and Applied Computing (Springer-12059)