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)
Preface

Working with Sequences

Let's look at another example to make the importance of sequence modeling clearer. The task is to predict the stock price for a company for the next 30 days. The data provided to you is the stock price for today. You can see this in the following plot, where the y-axis represents the stock price and the x-axis denotes the date. Is this data sufficient?

Figure 5.1: Stock price with just 1 day's data

Surely, one data point, that is, the price on a given day, is not sufficient to predict the price for the next 30 days. We need more information. Particularly, we need information about the past – how the stock price has been moving for the past few days/months/years. So, we ask for, and get, data for three years:

Figure 5.2: Stock price prediction using historical data

This seems much more useful, right? Looking at the past trend and some patterns in the data, we can make predictions on the...