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)


We started our journey in this chapter with an introduction to computer vision and image processing, where we learned the different applications of such technology, how digital images are represented, and analyzed this with filters.

Then, we dived into the basic elements of CNN. We learned what a convolution operation is, how filters work in detecting patterns, and what stride and padding are used for. After understanding these building blocks, we learned how to use TensorFlow to design CNN models. We built our own CNN architecture to recognize handwritten digits.

After this, we went through data generators and learned how they can feed our model with batches of images rather than loading the entire dataset. We also learned how they can perform data augmentation transformations to expand the variety of images and help the model generalize better.

Finally, we learned about saving a model and its configuration, but also about how to apply transfer learning and fine-tuning...