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

preview_player
Показать описание
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. 00:00 Welcome!
00:10 Help us add time stamps or captions to this video! See the description for details.

Рекомендации по теме
Комментарии
Автор

Great video to develop a simple mind model of neural networks. Bonus : frequentist vs. Bayesian made simple! Great work Eric!

ThierryAZALBERT
Автор

Love the charisma, enthusiasm put in this talk well done!

mherkhachatryan
Автор

1:00 Intro to Linear, Logistic regression, Neural Nets
9:40 Going Bayesian
14:32 Implementation Using PyMC3
24:27 QnA

harshraj_
Автор

Thank you so much! This has helped me so much with my project and really helped to understand both deep learning and bayesian deep learning much better. I really appreciate it!

suzystar
Автор

Huge win for my personal understanding on this topic. I wish every talk was given in this format. Thanks!

cnaccio
Автор

great energy! and nice philosophical wrap-up!

sdsa
Автор

I understand the benefit of modelling aleatoric uncertainty, e.g. to be able to deal with heteroscedastic noise.
However, why do we need to model epistemic uncertainty? The best prediction after all, lies in the middle of the final distribution. If you sample from the distribution, you will lose accuracy.
So is uncertainty only useful for certain applications to determine different behaviour based on high uncertainty? For example: If uncertainty is high, drive slower?

bracodescanner
Автор

The other presentation Eric mentions is that of Nicole Carlson:
Turning PyMC3 into scikit learn

catchenal
Автор

Point #1 is wrong. You left out activations.

vtrandal
Автор

Was he referring to Tensorflow when he denigrated an unnamed company for its non-pythonic API? The new Tensorflow is much better!

MiKenning