Discover the essential building blocks of a common and powerful form of deep belief network: convolutional nets. This book 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. These models are especially useful for image processing applications.
At each step Deep Belief Nets in C++ and CUDA C: Volume 3 presents 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. Source code for all routines presented in the book, and the executable CONVNET program which implements these algorithms, are available for free download.
What You Will Learn
- Discover convolutional nets and how to use them
- Build feedforward networks via wide versus deep nets, locally connected layers, pooling and output layers, and more
- Master the various programming algorithms required
- Carry out multi-threading gradient computations and memory allocations for this threading
- Work with CUDA code among the various layers, gradients, backpropagations and more
- Make use of the CONVNET manual provided to fully deal with convolution nets and the case study applied
Who This Book Is For
Those who have at least a basic knowledge of neural networks and some prior programming experience, although some C++ and CUDA C is recommended.
- ISBN: 978-1-4842-3720-5
- Editorial: Apress
- Encuadernacion: Rústica
- Páginas: 241
- Fecha Publicación: 19/01/2019
- Nº Volúmenes: 1
- Idioma: Inglés