Probabilistic Deep Learning

Synopsis of Probabilistic Deep Learning

«Probabilistic Deep Learning» is the guide to probabilistic deep learning by Oliver Duerr, Beate Sick and Elvis Murina (Manning, paperback, 296 pages, English).

Practical guide to probabilistic deep learning with Python, Keras and TensorFlow Probability. Starting from the principle of maximum likelihood, it teaches how to choose the right distribution for each data type and build Bayesian networks that quantify the uncertainty of their predictions. Includes exercises in Jupyter Notebooks.

Published on 10 November 2020. First edition.

For developers and data scientists with knowledge of Python and neural networks who want to incorporate uncertainty into their deep learning models.