Book Image

Advanced Deep Learning with Keras

By : Rowel Atienza
Book Image

Advanced Deep Learning with Keras

By: Rowel Atienza

Overview of this book

Recent developments in deep learning, including Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), and Deep Reinforcement Learning (DRL) are creating impressive AI results in our news headlines - such as AlphaGo Zero beating world chess champions, and generative AI that can create art paintings that sell for over $400k because they are so human-like. Advanced Deep Learning with Keras is a comprehensive guide to the advanced deep learning techniques available today, so you can create your own cutting-edge AI. Using Keras as an open-source deep learning library, you'll find hands-on projects throughout that show you how to create more effective AI with the latest techniques. The journey begins with an overview of MLPs, CNNs, and RNNs, which are the building blocks for the more advanced techniques in the book. You’ll learn how to implement deep learning models with Keras and TensorFlow 1.x, and move forwards to advanced techniques, as you explore deep neural network architectures, including ResNet and DenseNet, and how to create autoencoders. You then learn all about GANs, and how they can open new levels of AI performance. Next, you’ll get up to speed with how VAEs are implemented, and you’ll see how GANs and VAEs have the generative power to synthesize data that can be extremely convincing to humans - a major stride forward for modern AI. To complete this set of advanced techniques, you'll learn how to implement DRL such as Deep Q-Learning and Policy Gradient Methods, which are critical to many modern results in AI.

Related Content you might be interested in

Current Title:

Small book image
Advanced Deep Learning with Keras
Rowel Atienza
Oct, 2018 | 368 pages
Small book image
Hands-On Generative Adversarial Networks with Keras
Rafael Valle
May, 2019 | 272 pages
Small book image
Hands-On Image Generation with TensorFlow
Soon Yau Cheong
Dec, 2020 | 306 pages
Small book image
Generative Adversarial Networks Projects
Kailash Ahirwar
Jan, 2019 | 316 pages
Table of Contents (16 chapters)
Advanced Deep Learning with Keras
Advanced Deep Learning with Keras
Contributors
Contributors
Preface
Preface
Other Books You May Enjoy
Other Books You May Enjoy
Free Chapter
1
Introducing Advanced Deep Learning with Keras
Introducing Advanced Deep Learning with Keras
Why is Keras the perfect deep learning library?
Implementing the core deep learning models - MLPs, CNNs, and RNNs
Multilayer perceptrons (MLPs)
Convolutional neural networks (CNNs)
Recurrent neural networks (RNNs)
Conclusion
References
2
Deep Neural Networks
Deep Neural Networks
Functional API
Deep residual networks (ResNet)
ResNet v2
Densely connected convolutional networks (DenseNet)
Conclusion
References
3
Autoencoders
Autoencoders
Principles of autoencoders
Building autoencoders using Keras
Denoising autoencoder (DAE)
Automatic colorization autoencoder
Conclusion
References
4
Generative Adversarial Networks (GANs)
Generative Adversarial Networks (GANs)
An overview of GANs
Principles of GANs
GAN implementation in Keras
Conditional GAN
Conclusion
References
5
Improved GANs
Improved GANs
Wasserstein GAN
Least-squares GAN (LSGAN)
Auxiliary classifier GAN (ACGAN)
Conclusion
References
6
Disentangled Representation GANs
Disentangled Representation GANs
Disentangled representations
InfoGAN
Implementation of InfoGAN in Keras
Generator outputs of InfoGAN
StackedGAN
Implementation of StackedGAN in Keras
Generator outputs of StackedGAN
Conclusion
Reference
7
Cross-Domain GANs
Cross-Domain GANs
Principles of CycleGAN
The CycleGAN Model
Implementing CycleGAN using Keras
Generator outputs of CycleGAN
Conclusion
References
8
Variational Autoencoders (VAEs)
Variational Autoencoders (VAEs)
Principles of VAEs
Conditional VAE (CVAE)
-VAE: VAE with disentangled latent representations
Conclusion
References
9
Deep Reinforcement Learning
Deep Reinforcement Learning
Principles of reinforcement learning (RL)
The Q value
Q-Learning example
Q-Learning in Python
Nondeterministic environment
Temporal-difference learning
Q-Learning on OpenAI gym
Deep Q-Network (DQN)
DQN on Keras
Double Q-Learning (DDQN)
Conclusion
References
10
Policy Gradient Methods
Policy Gradient Methods
Policy gradient theorem
Monte Carlo policy gradient (REINFORCE) method
Conclusion
References
Index
Index

GAN implementation in Keras

In the previous section, we learned that the principles behind GANs are straightforward. We also learned how GANs could be implemented by familiar network layers such as CNNs and RNNs. What differentiates GANs from other networks is they are notoriously difficult to train. Something as simple as a minor change in the layers can drive the network to training instability.

In this section, we'll examine one of the early successful implementations of GANs using deep CNNs. It is called DCGAN [3].

Figure 4.2.1 shows DCGAN that is used to generate fake MNIST images. DCGAN recommends the following design principles:

  • Use of strides > 1 convolution instead of MaxPooling2D or UpSampling2D. With strides > 1, the CNN learns how to resize the feature maps.

  • Avoid using Dense layers. Use CNN in all layers. The Dense layer is utilized only as the first layer of the generator to accept the z-vector. The output of the Dense layer is resized and becomes the input of the succeeding...

Previous Section
End of Section 4
Next Section