Book Image

TensorFlow 1.x Deep Learning Cookbook

Book Image

TensorFlow 1.x Deep Learning Cookbook

Overview of this book

Deep neural networks (DNNs) have achieved a lot of success in the field of computer vision, speech recognition, and natural language processing. This exciting recipe-based guide will take you from the realm of DNN theory to implementing them practically to solve real-life problems in the artificial intelligence domain. In this book, you will learn how to efficiently use TensorFlow, Google’s open source framework for deep learning. You will implement different deep learning networks, such as Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Deep Q-learning Networks (DQNs), and Generative Adversarial Networks (GANs), with easy-to-follow standalone recipes. You will learn how to use TensorFlow with Keras as the backend. You will learn how different DNNs perform on some popularly used datasets, such as MNIST, CIFAR-10, and Youtube8m. You will not only learn about the different mobile and embedded platforms supported by TensorFlow, but also how to set up cloud platforms for deep learning applications. You will also get a sneak peek at TPU architecture and how it will affect the future of DNNs. By using crisp, no-nonsense recipes, you will become an expert in implementing deep learning techniques in growing real-world applications and research areas such as reinforcement learning, GANs, and autoencoders.
Table of Contents (15 chapters)
14
TensorFlow Processing Units

Creating a DeepDream network

Google trained a neural network on ImageNet for the Large Scale Visual Recognition Challenge (ILSVRC) in 2014 and made it open source in July 2015. The original algorithm is presented in Going Deeper with Convolutions, Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke e Andrew Rabinovich (https://arxiv.org/abs/1409.4842) . The network learned a representation of each image. The lower layers learned low-level features, such as lines and edges, while the higher layers learned more sophisticated patterns such as eyes, noses, mouths, and so on. Therefore, if we try to represent a higher level in the network, we will see a mix of different features extracted from the original ImageNet such as the eyes of a bird and the mouth of a dog. With this in mind, if we take a new image and try...