Book Image

Deep Learning with Keras

By : Antonio Gulli, Sujit Pal
Book Image

Deep Learning with Keras

By: Antonio Gulli, Sujit Pal

Overview of this book

This book starts by introducing you to supervised learning algorithms such as simple linear regression, the classical multilayer perceptron and more sophisticated deep convolutional networks. You will also explore image processing with recognition of handwritten digit images, classification of images into different categories, and advanced objects recognition with related image annotations. An example of identification of salient points for face detection is also provided. Next you will be introduced to Recurrent Networks, which are optimized for processing sequence data such as text, audio or time series. Following that, you will learn about unsupervised learning algorithms such as Autoencoders and the very popular Generative Adversarial Networks (GANs). You will also explore non-traditional uses of neural networks as Style Transfer. Finally, you will look at reinforcement learning and its application to AI game playing, another popular direction of research and application of neural networks.
Table of Contents (16 chapters)
Title Page
Credits
About the Authors
About the Reviewer
www.PacktPub.com
Customer Feedback
Preface

About the Authors

Antonio Gulli is a software executive and business leader with a passion for establishing and managing global technological talent, innovation, and execution. He is an expert in search engines, online services, machine learning, information retrieval, analytics, and cloud computing. So far, he has been lucky enough to gain professional experience in four different countries in Europe and managed people in six different countries in Europe and America. Antonio served as CEO, GM, CTO, VP, director, and site lead in multiple fields spanning from publishing (Elsevier) to consumer internet (Ask.com and Tiscali) and high-tech R&D (Microsoft and Google).

I would like to thank my coauthor, Sujit Pal, for being a such talented colleague, always willing to help with a humble spirit. I constantly appreciate his dedication to teamwork, which made this book a real thing.I would like to thank Francois Chollet (and the many Keras contributors) for taking the time and effort to build an awesome deep learning toolkit that is easy to use without sacrificing too much power.I would also like to thank our editors from Packt, Divya Poojari, Cheryl Dsa, and Dinesh Pawar, and our reviewers from Packt and Google, for their support and valuable suggestions. This book would not have been possible without you.I would like to thank my manager, Brad, and my colleagues Mike and Corrado at Google for encouraging me to write this book, and for their constant help in reviewing the content.I would like to thank Same Fusy, Herbaciarnia i Kawiarnia in Warsaw. I got the initial inspiration to write this book in front of a cup of tea chosen among hundreds of different offers. This place is magic and I strongly recommend visiting it if you are in search of  a place to stimulate creativeness (http://www.samefusy.pl/).Then I would like to thank HRBP at Google for supporting my wish to donate all of this book's royalties in favor of a minority/diversity scholarship.I would like to thank my friends Eric, Laura, Francesco, Ettore, and Antonella for supporting me when I was in need. Long-term friendship is a real thing, and you are true friends to me.I would like to thank my son Lorenzo for encouraging me to join Google, my son Leonardo for his constant passion to discover new things, and my daughter Aurora for making me smile every day of my life. Finally thanks to my father Elio and my mother Maria for their love.

Sujit Pal is a technology research director at Elsevier Labs, working on building intelligent systems around research content and metadata. His primary interests are information retrieval, ontologies, natural language processing, machine learning, and distributed processing. He is currently working on image classification and similarity using deep learning models. Prior to this, he worked in the consumer healthcare industry, where he helped build ontology-backed semantic search, contextual advertising, and EMR data processing platforms. He writes about technology on his blog at Salmon Run.

I would like to thank my coauthor, Antonio Gulli, for asking me to join him in writing this book. This was an incredible opportunity and a great learning experience for me. Besides, had he not done so, I quite literally wouldn't have been here today.I would like to thank Ron Daniel, the director of Elsevier Labs, and Bradley P Allen, chief architect at Elsevier, for introducing me to deep learning and making me a believer in its capabilities.I would also like to thank Francois Chollet (and the many Keras contributors) for taking the time and effort to build an awesome deep learning toolkit that is easy to use without sacrificing too much power.Thanks to our editors from Packt, Divya Poojari, Cheryl Dsa, and Dinesh Pawar, and our reviewers from Packt and Google, for their support and valuable suggestions. This book would not have been possible without you.I would like to thank my colleagues and managers over the years, especially the ones who took their chances with me and helped me make discontinuous changes in my career.Finally, I would like to thank my family for putting up with me these past few months as I juggled work, this book, and family, in that order. I hope you will agree that it was all worth it.