Аннотация
Development of artificial intelligent products and solutions has recently become a norm; hence, the demand for graph theory–based computational frameworks is on the rise. Making the deep learning models work in real-life applications is possible when the modeling framework is dynamic, flexible, and adaptable to other frameworks.
PyTorch is a recent entrant to the league of graph computation tools/programming languages. Addressing the limitations of previous frameworks, PyTorch promises a better user experience in the deployment of deep learning models, and the creation of advanced models using a combination of convolutional neural networks, recurrent neural networks, LSTMs, and deep neural networks.
PyTorch was created by Facebook’s Artificial Intelligence Research division, which seeks to make the model development process simple, straightforward, and dynamic, so that developers do not have to worry about declaring objects before compiling and executing the model. It is based on the Torch framework and is an extension of Python.
This book is intended for data scientists, natural language processing engineers, artificial intelligence solution developers, existing practitioners working on graph computation frameworks, and researchers of graph theory. This book will get you started with understanding tensor basics, computation, performing arithmetic-based operations, matrix algebra, and statistical distribution-based operations using the PyTorch framework.
Комментарии к книге "PyTorch Recipes"