Enhancing Deep Learning with Bayesian Inference: Create more powerful, robust deep learning systems with Bayesian deep learning in Python

Matt Benatan; Jochem Gietema; Marian Schneider

ISBN 10: 180324688X / ISBN 13: 9781803246888

Edité par Packt Publishing, 2023

A propos de cet article

N° de réf. du vendeur I-9781803246888

Détails bibliographiques

• Titre: Enhancing Deep Learning with Bayesian Inference: Create more powerful, robust deep learning systems with Bayesian deep learning in Python
• Éditeur: Packt Publishing
• Date de parution: 2023
• Langue: anglais
• ISBN à 10 chiffres: 180324688X
• ISBN à 13 chiffres: 9781803246888
• Reliure: Couverture souple
• État de l'article: New

A propos de ce titre

Synopsis

Develop Bayesian Deep Learning models to help make your own applications more robust.

Key Features

• Learn how advanced convolutions work
• Learn to implement a convolution neural network
• Learn advanced architectures using convolution neural networks
• Apply Bayesian NN to decrease weighted distribution

Book Description

Bayesian Deep Learning provides principled methods for developing deep learning models capable of producing uncertainty estimates.

Typical deep learning methods do not produce principled uncertainty estimates, i.e. they don’t know when they don’t know. Principled uncertainty estimates allow developers to handle unexpected scenarios in real-world applications, and therefore facilitate the development of safer, more robust systems.

Developers working with deep learning will be able to put their knowledge to work with this practical guide to Bayesian Deep Learning.

Learn building and understanding of how Bayesian Deep Learning can improve the way you work with models in production.

You’ll learn about the importance of uncertainty estimates in predictive tasks, and will be introduced to a variety of Bayesian Deep Learning approaches used to produce principled uncertainty estimates. You will be guided through the implementation of these approaches, and will learn how to select and apply Bayesian Deep Learning methods to real-world applications.

By the end of the book you will have a good understanding of Bayesian Deep Learning and the advantages it has to offer, and will be able to develop Bayesian Deep Learning models to help make your own applications more robust.

What you will learn

• Understanding the fundamentals of Bayesian Neural Networks
• Understanding the tradeoffs between different key BNN implementations/approximations
• Understanding the advantages of probabilistic DNNs in production contexts
• Knowing how to implement a variety of BDL methods, and how to apply these to real-world problems
• Understanding how to evaluate BDL methods and choose the best method for a given task

Who This Book Is For

Researchers and developers are looking for ways to develop more robust deep learning models through probabilistic deep learning.

The reader will know the fundamentals of machine learning, and have some experience of working with machine learning and deep learning models.

Table of Contents

1. Bayesian Inference in the Age of Deep Learning
2. Fundamentals of Bayesian Inference
3. Fundamentals of Deep Learning
4. Introducing Bayesian Deep Learning
5. Principled Approaches for Bayesian Deep Learning
6. Using the Standard Toolbox for Bayesian Deep Learning
7. Practical considerations for Bayesian Deep Learning
8. Applying Bayesian Deep Learning
9. Next steps in Bayesian Deep Learning

À propos des auteurs

Matt Benatan is a Principal Research Scientist at Sonos and a Simon Industrial Fellow at the University of Manchester. His work involves research in robust multimodal machine learning, uncertainty estimation, Bayesian optimization, and scalable Bayesian inference.

Jochem Gietema is an Applied Scientist at Onfido in London where he has developed and deployed several patented solutions related to anomaly detection, computer vision, and interactive data visualisation.

Marian Schneider is an applied scientist in machine learning. His work involves developing and deploying applications in computer vision, ranging from brain image segmentation and uncertainty estimation to smarter image capture on mobile devices.