Book Image

Neural Networks with Keras Cookbook

By : V Kishore Ayyadevara
Book Image

Neural Networks with Keras Cookbook

By: V Kishore Ayyadevara

Overview of this book

This book will take you from the basics of neural networks to advanced implementations of architectures using a recipe-based approach. We will learn about how neural networks work and the impact of various hyper parameters on a network's accuracy along with leveraging neural networks for structured and unstructured data. Later, we will learn how to classify and detect objects in images. We will also learn to use transfer learning for multiple applications, including a self-driving car using Convolutional Neural Networks. We will generate images while leveraging GANs and also by performing image encoding. Additionally, we will perform text analysis using word vector based techniques. Later, we will use Recurrent Neural Networks and LSTM to implement chatbot and Machine Translation systems. Finally, you will learn about transcribing images, audio, and generating captions and also use Deep Q-learning to build an agent that plays Space Invaders game. By the end of this book, you will have developed the skills to choose and customize multiple neural network architectures for various deep learning problems you might encounter.
Table of Contents (18 chapters)

Neural style transfer between images

In the previous recipe, the modified pixel values were trying to maximize the filter activations. However, it does not give us the flexibility of specifying the style of the image; neural style transfer comes in handy in this scenario.

In neural style transfer, we have a content image and a style image, and we try to combine these two images in such a way that the content in the content image is preserved while maintaining the style of the style image.

Getting ready

The intuition of neural style transfer is as follows.

We try to modify the original image in a similar way to the DeepDream algorithm. However, the additional step is that the loss value is split into content loss and style...