Probabilistic Deep Learning With Python, Keras and TensorFlow Probability

<b><i>Probabilistic Deep Learning</i> is a hands-on guide to the principles that support neural networks. Learn to improve network performance with the right distribution for different data types, and discover Bayesian variants that can state their own uncertainty to increase accuracy. This book provides easy-to-apply code and uses popular frameworks to keep you focused on practical applications.</b><br><br><b>Summary</b><br> <i>Probabilistic Deep Learning: With Python, Keras and TensorFlow Probability</i> teaches the increasingly popular probabilistic approach to deep learning that allows you to refine your results more quickly and accurately without much trial-and-error testing. Emphasizing practical techniques that use the Python-based Tensorflow Probability Framework, you’ll learn to build highly-performant deep learning applications that can reliably handle the noise and uncertainty of real-world data.<br> <br>Purchase of the print book includes a free eBook in PDF, Kindle, and ePub formats from Manning Publications.<br> <br> <b>About the technology</b><br> The world is a noisy and uncertain place. Probabilistic deep learning models capture that noise and uncertainty, pulling it into real-world scenarios. Crucial for self-driving cars and scientific testing, these techniques help deep learning engineers assess the accuracy of their results, spot errors, and improve their understanding of how algorithms work.<br> <br> <b>About the book</b><br> <i>Probabilistic Deep Learning</i> is a hands-on guide to the principles that support neural networks. Learn to improve network performance with the right distribution for different data types, and discover Bayesian variants that can state their own uncertainty to increase accuracy. This book provides easy-to-apply code and uses popular frameworks to keep you focused on practical applications.<br> <br> <b>What's inside</b><br> <br> Explore maximum likelihood and the statistical basis of deep learning<br> Discover probabilistic models that can indicate possible outcomes<br> Learn to use normalizing flows for modeling and generating complex distributions<br> Use Bayesian neural networks to access the uncertainty in the model<br> <br><b>About the reader</b><br> For experienced machine learning developers.<br> <br> <b>About the author</b><br> <b>Oliver Dürr</b> is a professor at the University of Applied Sciences in Konstanz, Germany. <b>Beate Sick</b> holds a chair for applied statistics at ZHAW and works as a researcher and lecturer at the University of Zurich. <b>Elvis Murina</b> is a data scientist.<br> <br><b>Table of Contents</b><br> <br>PART 1 - BASICS OF DEEP LEARNING<br> <br>1 Introduction to probabilistic deep learning<br> <br>2 Neural network architectures<br> <br>3 Principles of curve fitting<br> <br>PART 2 - MAXIMUM LIKELIHOOD APPROACHES FOR PROBABILISTIC DL MODELS<br> <br>4 Building loss functions with the likelihood approach<br> <br>5 Probabilistic deep learning models with TensorFlow Probability<br> <br>6 Probabilistic deep learning models in the wild<br> <br>PART 3 - BAYESIAN APPROACHES FOR PROBABILISTIC DL MODELS<br> <br>7 Bayesian learning<br> <br>8 Bayesian neural networks