Build neural network models theoretically using TensorFlow 2.0. with workable implementations. This new edition focuses on the practical aspects of implementing deep-learning solutions using the new deep learning framework TensorFlow 2.0 and in particular Keras with its rich Python ecosystem. Written with a more pedagogical approach, this book is designed so that you can focus on the parts you're interested in. Additionally, you'll explores recent advances in the field namely, autoencoders and multitask learning, A short chapter will also describe the differences between PyTorch and TensorFlow 2.0. The book also focuses on introducing you to key concepts of edge computing and automatic differentiation. TensorFlow lite for edge computing is covered to allow you to build models and deploy them on edge devices as Raspberry Pi or Coral devices from Google. All the code presented in the book will be available in the form of Jupyter notebooks and scripts which would allow you to try out these examples and extend them in interesting ways. A complete GitHub repository will be available with the complete code covered in this second edition. What You Will Learn Implement advanced deep learning techniques in the right way with Python and TensorFlow 2.0 Review edge computing and automatic differentiation Perform an error analysis to know if one has a bias problem, a variance, or a data offset problem Set up a AI project focused on deep learning on a complex datasets Who This Book Is For Readers with an intermediate understanding of machine learning, linear algebra, calculus, and basic Python programming.

Book Information
ISBN 9781484280195
Author Umberto Michelucci
Format Paperback
Page Count 540
Imprint APress
Publisher APress