Beginning Application Development with TensorFlow and Keras

English | 2018 | ISBN: 978-1789537291 | 148 Pages | PDF, EPUB | 12 MB

Learn to design, develop, train, and deploy TensorFlow and Keras models as real-world applications
With this book, you’ll learn how to train, evaluate and deploy Tensorflow and Keras models as real-world web applications. After a hands-on introduction, you’ll use a sample model to explore the details of deep learning, selecting the right layers that can solve a given problem. By the end of the course, you’ll build a Bitcoin application that predicts the future price, based on historic, and freely available information.
This book will also provide you with a blueprint for how to build an application that generates predictions using a deep learning model. From there, you can continue to improve our example model— either by adding more data, computing more features, or changing its architecture—continuously increasing its prediction accuracy, or create a completely new model, changing the core components of the application as you see fit.
What You Will Learn

• Set up a deep learning programming environment
• Explore the common components of a neural network and its essential operations
• Prepare data for a deep learning model
• Deploy model as an interactive web application, with Flask and a HTTP API
• Use Keras, a TensorFlow abstraction library
• Explore the types of problems addressed by neural networks