Which inductive bias?
61 karma · joined January 26, 2016
I agree with most of the article but I think this^^ skips over the different types of networks used to solve perception and language problems. A CNN is very different from say, word2vec, which isn't a very deep network at all.
Good link: "... which noted the diagnosis of chronic Lyme disease is used by a few physicians despite a lack of "reproducible or convincing scientific evidence", leading the authors to describe this diagnosis as "the latest in a series of syndromes that have been postulated in an attempt to attribute medically unexplained symptoms to particular infections."