Re:Failures of Deep Learning
by reader5000 on Saturday March 25, 2017 @12:59PM
(#13956512)
Code will be hard to follow outside of the particular language's community. There are efforts to standardize pseudo-code, but then you're basically back to math notation.
[ Parent
| on HN ]
Code has the advantage that functions and operators are googleable, while mathematical notation is not. I think the search problem is a fairly serious issue for maths actually.
Re:Failures of Deep Learning
by reader5000 on Saturday March 25, 2017 @04:08PM
(#13957323)
True, but it's not maths' fault Google and OSs dont support copy/paste for notation. Also, if you have to google e.g. the expectation operator you probably shouldnt be reading research papers in theoretical machine learning.
Re:Failures of Deep Learning
by abecedarius on Saturday March 25, 2017 @02:21PM
(#13956884)
And the even greater plus of being runnable. If it's confusing/ambiguous to you, you're not stuck.