Introducing Advanced Deep Learning with Keras
In this first chapter, we will introduce three deep learning artificial neural networks that we will be using throughout the book. These networks are MLP, CNN, and RNN (defined and described in Section 2), which are the building blocks of selected advanced deep learning topics covered in this book, such as autoregressive networks (autoencoder, GAN, and VAE), deep reinforcement learning, object detection and segmentation, and unsupervised learning using mutual information.
Together, we'll discuss how to implement MLP, CNN, and RNN based models using the Keras library in this chapter. More specifically, we will use the TensorFlow Keras library called tf.keras. We'll start by looking at why tf.keras is an excellent choice as a tool for us. Next, we'll dig into the implementation details within the three deep learning networks.
This chapter will:
- Establish why the
tf.keraslibrary is a great choice to use for advanced deep learning - Introduce MLP, CNN, and RNN – the core building blocks of advanced deep learning models, which we'll be using throughout this book
- Provide examples of how to implement MLP, CNN, and RNN based models using
tf.keras - Along the way, start to introduce important deep learning concepts, including optimization, regularization, and loss function
By the end of this chapter, we'll have the fundamental deep learning networks implemented using tf.keras. In the next chapter, we'll get into the advanced deep learning topics that build on these foundations. Let's begin this chapter by discussing Keras and its capabilities as a deep learning library.
