Eric J. Ma - An Attempt At Demystifying Bayesian Deep Learning

Thanks! Share it with your friends!

You disliked this video. Thanks for the feedback!

Added by admin
PyData New York City 2017


In this talk, I aim to do two things: demystify deep learning as essentially matrix multiplications with weights learned by gradient descent, and demystify Bayesian deep learning as placing priors on weights. I will then provide PyMC3 and Theano code to illustrate how to construct Bayesian deep nets and visualize uncertainty in their results.
PyData New York 2017

Post your comment