Book Image

Neural Network Programming with Tensorflow

By : Manpreet Singh Ghotra, Rajdeep Dua
Book Image

Neural Network Programming with Tensorflow

By: Manpreet Singh Ghotra, Rajdeep Dua

Overview of this book

If you're aware of the buzz surrounding the terms such as "machine learning," "artificial intelligence," or "deep learning," you might know what neural networks are. Ever wondered how they help in solving complex computational problem efficiently, or how to train efficient neural networks? This book will teach you just that. You will start by getting a quick overview of the popular TensorFlow library and how it is used to train different neural networks. You will get a thorough understanding of the fundamentals and basic math for neural networks and why TensorFlow is a popular choice Then, you will proceed to implement a simple feed forward neural network. Next you will master optimization techniques and algorithms for neural networks using TensorFlow. Further, you will learn to implement some more complex types of neural networks such as convolutional neural networks, recurrent neural networks, and Deep Belief Networks. In the course of the book, you will be working on real-world datasets to get a hands-on understanding of neural network programming. You will also get to train generative models and will learn the applications of autoencoders. By the end of this book, you will have a fair understanding of how you can leverage the power of TensorFlow to train neural networks of varying complexities, without any hassle. While you are learning about various neural network implementations you will learn the underlying mathematics and linear algebra and how they map to the appropriate TensorFlow constructs.
Table of Contents (17 chapters)
Title Page
About the Authors
About the Reviewer
Customer Feedback

Computational graph

TensorFlow is based on building a computational graph. A computational graph is a network of nodes, where each node defines an operation running a function; this can be as plain as addition or subtraction, or as complicated as a multivariate equation. TensorFlow programs are structured in a construction phase that assembles a graph and an execution phase that utilizes a session object to execute operations in the graph.

An operation is referred to as the op and can return zero or more tensors, which can be used later in the graph. Each op can be given a constant, array, or n-dimensional matrix. 


The default graph gets instantiated when the TensorFlow library is imported. Constructing a graph object instead of using the default graph is useful when creating multiple models in one file that do not depend on each other. Constants and operations are added to the graph in TensorFlow.

Variables and operations applied outside of newGraph.as_default() will get added to the...