GANs in Action

GANs are a promising solution to creating realistic images, natural sentences, and paragraphs, or native-quality translations. This course teaches you how to build and train your own GAN models, with hands-on code tutorials and advanced architectures. It is written for data scientists and data analysts with intermediate Python knowledge, and covers practical applications of GANs.

Format: Paperback / softback
Length: 276 pages
Publication date: 28 October 2019
Publisher: Manning Publications

Deep learning systems have made significant strides in identifying patterns in various forms of data, including text, images, and video. However, the creation of realistic images, natural sentences, and paragraphs, or high-quality translations, remains a challenge. Enter Generative Adversarial Networks (GANs), a promising solution to these obstacles.

GANs are a type of neural network that consists of two competing sub-networks. The first sub-network, known as the generator, is responsible for generating new content, while the second sub-network, called the discriminator, evaluates the quality of the generated content. These two sub-networks work in tandem to improve the overall performance of the GAN.

In this comprehensive course, "GANs in Action: Deep Learning with Generative Adversarial Networks," you will delve into the world of GANs and learn how to build and train your own generative adversarial networks. You will begin by gaining an introduction to generative modeling and understanding how GANs work. You will then explore the fundamental components of GAN architecture, including the generator and discriminator networks.

Throughout the course, you will engage in hands-on code tutorials that will guide you through the process of building GAN models. You will cover advanced GAN architectures and techniques, such as Cycle-Consistent Adversarial Networks, which aim to address the progressive growing of GANs. You will also learn practical applications of GANs in fields such as image generation, text generation, and video synthesis.

This course is designed for data scientists and data analysts with intermediate Python knowledge. It assumes a basic understanding of deep learning concepts, but no prior knowledge of GANs is required. By the end of the course, you will have gained a deep understanding of GANs and their potential applications, and you will be equipped with the skills to build and train your own generative adversarial networks.

GANs have already achieved remarkable results in various domains, including realistic face generation, image-to-image translation, and video-to-video translation. These achievements demonstrate the power of GANs and their ability to learn quickly without the need for vast amounts of labeled training data.

The course is authored by Jakub Langr, a graduate of Oxford University and a former teaching assistant at OU. Jakub has extensive experience in the field of deep learning and has published research papers in top-tier conferences and journals. His expertise and passion for the subject will ensure that you receive a comprehensive and engaging learning experience.

Enroll in "GANs in Action: Deep Learning with Generative Adversarial Networks" today and unlock the full potential of this exciting technology.

Weight: 468g
Dimension: 187 x 234 x 14 (mm)
ISBN-13: 9781617295560