Book Image

The Deep Learning Workshop

By : Mirza Rahim Baig, Thomas V. Joseph, Nipun Sadvilkar, Mohan Kumar Silaparasetty, Anthony So
Book Image

The Deep Learning Workshop

By: Mirza Rahim Baig, Thomas V. Joseph, Nipun Sadvilkar, Mohan Kumar Silaparasetty, Anthony So

Overview of this book

Are you fascinated by how deep learning powers intelligent applications such as self-driving cars, virtual assistants, facial recognition devices, and chatbots to process data and solve complex problems? Whether you are familiar with machine learning or are new to this domain, The Deep Learning Workshop will make it easy for you to understand deep learning with the help of interesting examples and exercises throughout. The book starts by highlighting the relationship between deep learning, machine learning, and artificial intelligence and helps you get comfortable with the TensorFlow 2.0 programming structure using hands-on exercises. You’ll understand neural networks, the structure of a perceptron, and how to use TensorFlow to create and train models. The book will then let you explore the fundamentals of computer vision by performing image recognition exercises with convolutional neural networks (CNNs) using Keras. As you advance, you’ll be able to make your model more powerful by implementing text embedding and sequencing the data using popular deep learning solutions. Finally, you’ll get to grips with bidirectional recurrent neural networks (RNNs) and build generative adversarial networks (GANs) for image synthesis. By the end of this deep learning book, you’ll have learned the skills essential for building deep learning models with TensorFlow and Keras.
Table of Contents (9 chapters)


You have come a long way from being introduced to one of the most promising areas in deep learning. Let's revisit some of the concepts that we learned about in this chapter.

We started this chapter by understanding what GANs are and their major applications. We then went on to understand the various building blocks of GANs, such as the real datasets, fake datasets, the discriminator operation, the generator operation, and the GAN operation.

We executed a problem statement to progressively build a fully connected GAN (FCGAN) to solve a real function. In the process of building the GAN, we also implemented exercises for creating real datasets, creating fake datasets, creating a generator network, creating a discriminator network, and finally combining all these individual components to create the GAN. We visualized the different plots and understood how the generated data distribution mimicked the real data distribution.

In the next section, we understood the...