News for hackers. Stuff that matters.

A comment on Ask HN: What are the best MOOCs you've taken?. Parent comment

Re:Ask HN: What are the best MOOCs you've taken? by mr_overalls on Tuesday April 03, 2018 @12:50PM (#16746560)
Is PGM still relevant as it was five years ago, given the renaissance in deep learning and other NN techniques?
[ Parent | on HN ]
Re:Ask HN: What are the best MOOCs you've taken? by matiasz on Tuesday April 03, 2018 @01:05PM (#16746744)
Yes [1].

[1] https://arxiv.org/abs/1801.04016

[ Parent | on HN ]
Re:Ask HN: What are the best MOOCs you've taken? by plafl on Tuesday April 03, 2018 @02:10PM (#16747441)
For me Bayesian networks are a tool of thought and I think it's worthy to learn them in the same way it's worthy to learn to sketch functions with pen and paper.
[ Parent | on HN ]
Re:Ask HN: What are the best MOOCs you've taken? by swframe2 on Tuesday April 03, 2018 @04:38PM (#16748887)
Checkout http://edwardlib.org/ and https://www.tensorflow.org/api_docs/python/tf/contrib/bayesf....

Also Bayesian Methods for Hackers: https://news.ycombinator.com/item?id=16482421

[ Parent | on HN ]
Re:Ask HN: What are the best MOOCs you've taken? by ansible on Tuesday April 03, 2018 @06:23PM (#16749932)
Yes, I think so. PGM or some improvement on that is relevant to doing things like reasoning correctly based on evidence.

I envision more sophisticated AGI systems to use DNN or other NN techniques to learn about the world, and be able to take in uncertain input and make sense of it. PGM or similar would then be used to correctly (in the mathematical sense) reason about what to do to accomplish the agent's goals.

[ Parent | on HN ]
Re:Ask HN: What are the best MOOCs you've taken? by parsthis on Tuesday April 03, 2018 @08:45PM (#16750862)
Also graphical models are combined with deep learning techniques for SOTA performance in area like Named Entity Recognition.
[ Parent | on HN ]