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)

Classical Approaches to Text Representation

Text representation approaches have evolved significantly over the years, and the advent of neural networks and deep neural networks has made a significant impact on the way we now represent text (more on that later). We have come a long way indeed: from handcrafting features to marking if a certain word is present in the text, to creating powerful representations such as word embeddings. While there are a lot of approaches, some more suitable for the task than the others, we will discuss a few major classical approaches and work with all of them in Python.

One-Hot Encoding

One-hot encoding is, perhaps, one of the most intuitive approaches toward text representation. A one-hot encoded feature for a word is a binary indicator of the term being present in the text. It's a simple approach that is easy to interpret – the presence or absence of a word. To understand this better, let's consider our sample text before stemming...