Deep Bayesian Networks -- Beyond Deep Neural Networks

What we will discuss?

How to make deep learning deal with the uncertainties of the real world? The answer is in deep Bayesian networks. We will be discussing Bayes' theorem and it's surprisingly effective role in helping deep learning models deal with uncertainties.

Who is the target audience?

Participants interested in understanding the current trends in deep-learning and in Bayesian networks.

Why this topic?

One of the real world adoption issues with deep neural networks is their inability to properly quantify and address uncertainties. Bayesian approach towards deep learning is a promising solution to this challenge.

Important to know:
Please bring a valid ID to sign-in at the front desk. Please provide your full first and last names in the ID.
This is an introductory workshop on machine vision. This course is part of the FutureReady boot-camp by Moad Computer. If you are interested in participating in the boot-camp, please fill-out this form: https://goo.gl/forms/TzClAtTqOLwHcudv1

Additional materials:
Deep Learning Is Not Good Enough, We Need Bayesian Deep Learning for Safe AI, by Alex Kendall: https://alexgkendall.com/computer_vision/bayesian_deep_learning_for_safe_ai/
NIPS 2018 workshop on Bayesian deep learning: http://bayesiandeeplearning.org/
Building a Bayesian deep learning classifier, by Kyle Dorman via Towards Data Science : https://towardsdatascience.com/building-a-bayesian-deep-learning-classifier-ece1845bc09