© Timothy Masters 2018
Timothy MastersDeep Belief Nets in C++ and CUDA C: Volume 3https://doi.org/10.1007/978-1-4842-3721-2_2

2. Programming Algorithms

Timothy Masters1 
(1)
Ithaca, New York, USA
 
The source code that can be downloaded for free from my web site contains four large source files that handle the vast majority of the computation involved in propagating activations and backpropagating deltas for all layer types involved in convolutional nets.
  • MOD_NO_THR.CPP : Nonthreaded versions of all routines. These are not used in the CONVNET program, but they are the routines listed and discussed in this book. Because they are not designed for threaded use, they are somewhat simpler than the threaded versions. In this way, the focus of discussion can ...

Get Deep Belief Nets in C++ and CUDA C: Volume 3: Convolutional Nets now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.