1. 7

  2. 4

    I had almost skipped the article because the title suggested an opinion piece. I am glad I didn’t: the article lays out a clear problem, discusses how Bayesian deep learning can solve it, shows examples of B.d.l. in action, and links to research papers.

    For those wondering whether to read it, this paragraph should give you an idea.

    The main issue is that traditional machine learning approaches to understanding uncertainty, such as Gaussian processes, do not scale to high dimensional inputs like images and videos. To effectively understand this data, we need deep learning. But deep learning struggles to model uncertainty.In this post I’m going to introduce a resurging field known as Bayesian deep learning (BDL), which provides a deep learning framework which can also model uncertainty.

    1. 1

      I mean that was the title on the article. I’m not sure I could have provided to help.

      1. 2

        Oh, I agree! I did not mean to blame you, and I am sorry that I gave that impression.

        I mentioned the title to make clear my own mistake (prejudging an article by its title), in the hope that I might prevent others from making the same mistake.

        Finally, thank you for posting this article. I found it very interesting indeed, and enjoyed reading it.