Probabilistic deep learning : with Python, Keras, and TensorFlow Probability /

Saved in:

Bibliographic Details
Author / Creator:	Dürr, Oliver (College teacher), author.
Imprint:	Shelter Island, New York : Manning Publications, [2020] ©2020
Description:	1 online resource
Language:	English
Subject:	Machine learning. Neural networks (Computer science) Computer programming. Machine learning Neural networks (Computer science)
Format:	E-Resource Book
URL for this record:	http://pi.lib.uchicago.edu/1001/cat/bib/13686559

Hidden Bibliographic Details
Other authors / contributors:	Sick, Beate, author. Murina, Elvis, author.
ISBN:	9781638350408 163835040X 1617296074 9781617296079 9781617296079
Notes:	"Exercises in Jupyter Notebooks"--Cover Includes bibliographical references.
Summary:	Probabilistic Deep Learning 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.
Other form:	Print version: Sick, Beate Probabilistic Deep Learning New York : Manning Publications Co. LLC,c2020 9781617296079

Table of Contents:

Part 1, Basics of deep learning. Introduction to probabilistic deep learning ; Neural network architectures ; Principles of curve fitting
Part 2, Maximum likelihood approaches for probabilistic DL models. Building loss functions with the likelihood approach ; Probabilistic deep learning models with TensorFlow Probability ; Probabilistic deep learning models in the wild
Part 3, Bayesian approaches for probabilistic DL models. Bayesian learning ; Bayesian neural networks.

Similar Items