#### 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.
Title Page
Credits
www.PacktPub.com
Customer Feedback
Preface
Free Chapter
Maths for Neural Networks
Deep Feedforward Networks
Optimization for Neural Networks
Convolutional Neural Networks
Recurrent Neural Networks
Generative Models
Autoencoders
Research in Neural Networks
Getting started with TensorFlow

## Chapter 5. Recurrent Neural Networks

Recurrent Neural Networks (RNNs) make use of sequential or time series data. In a regular neural network, we consider that all inputs and outputs are independent of each other. For a task where you want to predict the next word in a given sentence, it's better to know which words have come before it. RNNs are recurrent as the same task is performed for every element in the sequence where the output is dependent on the previous calculations. RNNs can be thought of as having a memory that captures information about what has been computed so far.

Going from feedforward neural networks to recurrent neural networks, we will use the concept of sharing parameters across various parts of the model. Parameter sharing will make it possible to extend and apply the model to examples of different forms (different lengths, here) and generalize across them.