LEADER 03800nam  22006255  450 
001 9910300747503321
005 20200703082830.0
010   $a1-4842-3591-6
024 7 $a10.1007/978-1-4842-3591-1
035   $a(CKB)4100000003359121
035   $a(MiAaPQ)EBC5356209
035   $a(DE-He213)978-1-4842-3591-1
035   $a(CaSebORM)9781484235911
035   $a(PPN)226699471
035   $a(OCoLC)1037100034
035   $a(OCoLC)on1037100034
035   $a(EXLCZ)994100000003359121
100   $a20180423d2018      u|         0
101 0 $aeng
135   $aurcnu||||||||
181   $ctxt$2rdacontent
182   $cc$2rdamedia
183   $acr$2rdacarrier
200 10$aDeep Belief Nets in C++ and CUDA C: Volume 1 $eRestricted Boltzmann Machines and Supervised Feedforward Networks /$fby Timothy Masters
205   $a1st ed. 2018.
210  1$aBerkeley, CA :$cApress :$cImprint: Apress,$d2018.
215   $a1 online resource (225 pages) $cillustrations
300   $aIncludes index.
311   $a1-4842-3590-8 
327   $a1. Introduction -- 2. Supervised Feedforward Networks -- 3. Restricted Boltzmann Machines -- 4. Greedy Training: Generative Samplings -- 5. DEEP Operating Manual.
330   $aDiscover 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.
517 3 $aRestricted Boltzmann machines and supervised feedforward networks
517 3 $aDeep Belief Nets in C plus plus and CUDA C
606   $aArtificial intelligence
606   $aProgramming languages (Electronic computers)
606   $aBig data
606   $aArtificial Intelligence$3https://scigraph.springernature.com/ontologies/product-market-codes/I21000
606   $aProgramming Languages, Compilers, Interpreters$3https://scigraph.springernature.com/ontologies/product-market-codes/I14037
606   $aBig Data$3https://scigraph.springernature.com/ontologies/product-market-codes/I29120
606   $aBig Data/Analytics$3https://scigraph.springernature.com/ontologies/product-market-codes/522070
615  0$aArtificial intelligence.
615  0$aProgramming languages (Electronic computers).
615  0$aBig data.
615 14$aArtificial Intelligence.
615 24$aProgramming Languages, Compilers, Interpreters.
615 24$aBig Data.
615 24$aBig Data/Analytics.
676   $a006.32
700   $aMasters$b Timothy$4aut$4http://id.loc.gov/vocabulary/relators/aut$0105163
801  0$bUMI
801  1$bUMI
906   $aBOOK
912   $a9910300747503321
996   $aDeep Belief Nets in C++ and CUDA C: Volume 1$92497770
997   $aUNINA