Muutke küpsiste eelistusi

E-raamat: Generating a New Reality: From Autoencoders and Adversarial Networks to Deepfakes

5.00/5 (2 hinnangut Goodreads-ist)
  • Formaat: PDF+DRM
  • Ilmumisaeg: 15-Jul-2021
  • Kirjastus: APress
  • Keel: eng
  • ISBN-13: 9781484270929
Teised raamatud teemal:
  • Formaat - PDF+DRM
  • Hind: 67,91 €*
  • * hind on lõplik, st. muud allahindlused enam ei rakendu
  • Lisa ostukorvi
  • Lisa soovinimekirja
  • See e-raamat on mõeldud ainult isiklikuks kasutamiseks. E-raamatuid ei saa tagastada.
Generating a New Reality: From Autoencoders and Adversarial Networks to DeepfakesSuurem pilt
  • Formaat: PDF+DRM
  • Ilmumisaeg: 15-Jul-2021
  • Kirjastus: APress
  • Keel: eng
  • ISBN-13: 9781484270929
Teised raamatud teemal:

DRM piirangud

  • Kopeerimine (copy/paste):

    ei ole lubatud

  • Printimine:

    ei ole lubatud

  • Kasutamine:

    Digitaalõiguste kaitse (DRM)
    Kirjastus on väljastanud selle e-raamatu krüpteeritud kujul, mis tähendab, et selle lugemiseks peate installeerima spetsiaalse tarkvara. Samuti peate looma endale  Adobe ID Rohkem infot siin. E-raamatut saab lugeda 1 kasutaja ning alla laadida kuni 6'de seadmesse (kõik autoriseeritud sama Adobe ID-ga).

    Vajalik tarkvara
    Mobiilsetes seadmetes (telefon või tahvelarvuti) lugemiseks peate installeerima selle tasuta rakenduse: PocketBook Reader (iOS / Android)

    PC või Mac seadmes lugemiseks peate installima Adobe Digital Editionsi (Seeon tasuta rakendus spetsiaalselt e-raamatute lugemiseks. Seda ei tohi segamini ajada Adober Reader'iga, mis tõenäoliselt on juba teie arvutisse installeeritud )

    Seda e-raamatut ei saa lugeda Amazon Kindle's. 

The emergence of artificial intelligence (AI) has brought us to the precipice of a new age where we struggle to understand what is real, from advanced CGI in movies to even faking the news. AI that was developed to understand our reality is now being used to create its own reality. 

In this book we look at the many AI techniques capable of generating new realities. We start with the basics of deep learning. Then we move on to autoencoders and generative adversarial networks (GANs). We explore variations of GAN to generate content. The book ends with an in-depth look at the most popular generator projects.

By the end of this book you will understand the AI techniques used to generate different forms of content. You will be able to use these techniques for your own amusement or professional career to both impress and educate others around you and give you the ability to transform your own reality into something new.


What You Will Learn
  • Know the fundamentals of content generation from autoencoders to generative adversarial networks (GANs)
  • Explore variations of GAN
  • Understand the basics of other forms of content generation
  • Use advanced projects such as Faceswap, deepfakes, DeOldify, and StyleGAN2


Who This Book Is For

Machine learning developers and AI enthusiasts who want to understand AI content generation techniques



Beginning-Intermediate user l;evel
About the Author ix
About the Technical Reviewer xi
Acknowledgments xiii
Introduction xv
Chapter 1 The Basics of Deep Learning
1(34)
Prerequisites
2(2)
The Perceptron
4(10)
The Multilayer Perceptron
14(2)
Backpropagation
16(1)
Stochastic Gradient Descent
17(1)
PyTorch and Deep Learning
18(3)
Understanding Regression
21(5)
Over- and Underfitting
26(1)
Classifying Classes
27(2)
One-Hot Encoding
29(1)
Classifying MNIST Digits
30(3)
Conclusion
33(2)
Chapter 2 Unleashing Generative Modeling
35(34)
Unsupervised Learning with Autoencoders
36(7)
Extracting Features with Convolution
43(7)
The Convolutional Autoencoder
50(5)
Generative Adversarial Networks
55(8)
Deep Convolutional GAN
63(5)
Conclusion
68(1)
Chapter 3 Exploring the Latent Space
69(36)
Understanding What Deep Learning Learns
70(1)
Deep Learning Function Approximation
71(4)
The Limitations of Calculus
75(1)
Deep Learning Hill Climbing
76(4)
Over- and Underfitting
80(6)
Building a Variational Autoencoder
86(4)
Learning Distributions with the VAE
90(9)
Variability and Exploring the Latent Space
99(3)
Conclusion
102(3)
Chapter 4 GANs, GANs, and More GANs
105(30)
Feature Understanding and the DCGAN
106(6)
Unrolling the Math of GANs
112(4)
Resolving Distance with WGAN
116(4)
Discretizing Boundary-Seeking GANs
120(4)
Relativity and the Relativistic GAN
124(5)
Conditioning with CGAN
129(4)
Conclusion
133(2)
Chapter 5 Image to Image Content Generation
135(32)
Segmenting Images with a UNet
136(6)
Uncovering the Details of a UNet
142(3)
Translating Images with Pix2Pix
145(6)
Seeing Double with the DualGAN
151(5)
Riding the Latent Space on the BicycleGAN
156(5)
Discovering Domains with the DiscoGAN
161(4)
Conclusion
165(2)
Chapter 6 Residual Network GANs
167(28)
Understanding Residual Networks
168(6)
Cycling Again with CycleGAN
174(6)
Creating Faces with StarGAN
180(4)
Using the Best with Transfer Learning
184(5)
Increasing Resolution with SRGAN
189(4)
Conclusion
193(2)
Chapter 7 Attention Is All We Need!
195(28)
What Is Attention?
196(3)
Understanding the Types of Attention
199(2)
Applying Attention
201(4)
Augmenting Convolution with Attention
205(4)
Lipschitz Continuity in GANs
209(1)
What Is Lipschitz Continuity?
209(5)
Building the Self-Attention GAN
214(4)
Improving on the SAGAN
218(4)
Conclusion
222(1)
Chapter 8 Advanced Generators
223(32)
Progressively Growing GANs
224(6)
Styling with StyleGAN Version 2
230(1)
Mapping Networks
231(1)
Style Modules
232(2)
Frechet Inception Distance
234(2)
StyleGAN2
236(6)
DeOldify and the New NoGAN
242(5)
Colorizing and Enhancing Video
247(2)
Being Artistic with ArtLine
249(4)
Conclusion
253(2)
Chapter 9 Deepfakes and Face Swapping
255(32)
Introducing the Tools for Face Swapping
257(3)
Gathering the Swapping Data
260(3)
Downloading YouTube Videos for Deepfakes
263(4)
Understanding the Deepfakes Workflow
267(2)
Extracting Faces
269(2)
Sorting and Trimming Faces
271(3)
Realigning the Alignments File
274(2)
Training a Face Swapping Model
276(3)
Creating a Deepfake Video
279(3)
Encoding the Video
282(2)
Conclusion
284(3)
Chapter 10 Cracking Deepfakes
287(13)
Understanding Face Manipulation Methods
288(3)
Techniques for Cracking Fakes
291(1)
Handcrafted Features
292(2)
Learning-Based Features
294(2)
Artifacts
296(3)
Identifying Fakes in Deepfakes
299(1)
Conclusion 300(3)
Appendix A Running Google Colab Locally 303(4)
Appendix B Opening a Notebook 307(2)
Appendix C Connecting Google Drive and Saving 309(4)
Index 313
Micheal Lanham is a proven software and tech innovator with more than 20 years of experience. During that time, he has developed a broad range of software applications in areas including games, graphics, web, desktop, engineering, artificial intelligence (AI), GIS, and machine learning (ML) applications for a variety of industries as an R&D developer. At the turn of the millennium, Micheal began working with neural networks and evolutionary algorithms in game development. He is an avid educator, has written more than eight books covering game development, extended reality, and AI, and teaches at meetups and other events. Micheal also likes to cook for his large family in his hometown of Calgary, Canada.
Lisainfo e-raamatute kohta Lisainfo e-raamatute kohta
Püsilink: https://www.kriso.ee/db/97814842709292e.html
Märksõnad: