Generative Adversarial Networks with Industrial Use Cases: Learning How to Build GAN Applications for Retail, Healthcare, Telecom, Media, Education, and HRTech
- Length: 132 pages
- Edition: 1
- Language: English
- Publisher: BPB Publications
- Publication Date: 2020-03-05
- ISBN-10: 9389423856
- ISBN-13: 9789389423853
- Sales Rank: #1736636 (See Top 100 Books)
Best Book on GAN
Key FeaturesUnderstanding the deep learning landscape and GAN’s relevance Learning basics of GANLearning how to build GAN from scratch Understanding mathematics and limitations of GAN Understanding GAN applications for Retail, Healthcare, Telecom, Media and EduTechUnderstanding the important GAN papers such as pix2pixGAN, styleGAN, cycleGAN, DCGAN Learning how to build GAN code for industrial applications Understanding the difference between varieties of GAN
Description
This book aims at simplifying GAN for everyone. This book is very important for machine learning engineers, researchers, students, professors, and professionals. Universities and online course instructors will find this book very interesting for teaching advanced deep learning, specially Generative Adversarial Networks(GAN). Industry professionals, coders, and data scientists can learn GAN from scratch. They can learn how to build GAN codes for industrial applications for Healthcare, Retail, HRTech, EduTech, Telecom, Media, and Entertainment. Mathematics of GAN is discussed and illustrated. KL divergence and other parts of GAN are illustrated and discussed mathematically. This book teaches how to build codes for pix2pix GAN, DCGAN, CGAN, styleGAN, cycleGAN, and many other GAN. Machine Learning and Deep Learning Researchers will learn GAN in the shortest possible time with the help of this book.
What will you learn
Machine Learning Researchers would be comfortable in building advanced deep learning codes for Industrial applications Data Scientists would start solving very complex problems in deep learning Students would be ready to join an industry with these skills Average data engineers and scientists would be able to develop complex GAN codes to solve the toughest problems in computer vision
Who this book is for
This book is perfect for machine learning engineers, data scientists, data engineers, deep learning professionals and computer vision researchers. This book is also very useful for medical imaging professionals, autonomous vehicles professionals, retail fashion professionals, media & entertainment professional, edutech and HRtech professionals. Professors and Students working in machine learning, deep learning, computer vision and industrial applications would find this book extremely useful.
About the Author
Navin K Manaswi has been developing AI solutions/products for HRTech, Retail, ITSM, Healthcare, Telecom, Insurance, Digital Marketing, and Supply Chain while working for Consulting companies in Malaysia, Singapore, and Dubai . He is a serial entrepreneur in Artificial Intelligence and Augmented Reality Space. He has been building solutions for video intelligence, document intelligence, and human-like chatbots. He is Guest Faculty at IIT Kharagpur for AI Course and an author of the famous book on deep learning. He is officially a Google Developer Expert in machine learning. He has been organizing and mentoring AI hackathons and boot camps at Google events and college events. His startup WoWExp has been building awesome products in AI and AR space.
Cover Page Title Page Copyright Page Dedication About the Author Acknowledgement Preface Errata Table of Contents 1. Basics of Generative Adversarial Networks (GAN) Introduction Structure Objectives Deep learning applications at a glance Types of deep learning applications Image classification Semantic segmentation Semantic search Text classification Generating images Generator Discriminator Object detection Multi-variate time series prediction Information extraction from the scan Different deep learning frameworks Introduction to GAN GAN architecture and explanation Getting started with GAN Task Dataset Data extraction Preprocessing the images Architecture of generator Architecture of discriminator Noise Loss How does it work? Optimizer Training Output Conclusion 2. GAN Applications Introduction Structure Objective Health sectorspecific GAN applications Health data generation Generating multi-label discrete patient records using GAN MedGAN Medical image translation using GANs MedGANarchitecture pix2pix PAN ID-CGAN ID-CGAN architecture Fila-SGAN Synthetic medical images from dual generative adversarial networks Why do we need? seGAN - medical image segmentation Anomaly detection Retail sector-specific GAN applications SRGAN Virtual try-on clothes Denoising images Sketch to (colorful/realistic)handbag/shoes Pose guided person image generation PixelDTGAN-taking clothes from celebrity pictures Disco GAN pix2pix - removing the filter from face Media and entertainment sector-specific GAN applications SRGAN DeOldify Stack GAN Face ageing - Age-cGAN Domain Transfer Networks (DTN) DTN architecture Autonomous vehicles sector-specific GAN applications Autonomous driving testing system EduTechsector-specific GAN applications pix2pix SRGAN Denoising GAN Image editing - IcGAN Telecom sector-specific GAN applications WaveNet GANSynth Mixed reality specific GAN applications Conclusion References 3. Problem with GAN Introduction The objective function for training GAN KL divergence KL divergence between two discrete probability distributions KL Divergence between two continuous probability distributions Nash equilibrium Prisoner’s dilemma Example The mentality behind solving GAN training problems Mode collapse Instability of adversarial training Lack of a proper evaluation metric Vanishing gradient Improving training One-sided label smoothing Virtual batch normalization (VBN) Adding noises Minibatch discrimination Use a better metric of distribution similarity Wasserstein GAN (WGAN) Wasserstein distance Why is Wasserstein better than JS or KL divergence? Wasserstein distance as GAN loss function Conclusion 4. Famous Types of GANs Structure Objective Generative Adversarial Network Training GAN’s Conditional Generative Adversarial Network (cGAN) Applications Architecture Mini-Maxcondition in cGAN LOSS DCGAN The generator The discriminator Applications InfoGAN Coding in InfoGAN Theory Architecture Results Pix2Pix Components of Pix2Pix model Architecture Generator Discriminator Results pix2pix application PAN ID-CGAN Stack GAN Conditioning augmentation Stage I Stage II Cycle GAN CycleGAN transfers styles to images Coding implementation: Style GAN Mapping network Style modules (AdaIN) Removing initial input Stochastic variation Style mixing Truncation trick in W Radial GAN Conclusion Exercise
Donate to keep this site alive
1. Disable the AdBlock plugin. Otherwise, you may not get any links.
2. Solve the CAPTCHA.
3. Click download link.
4. Lead to download server to download.