-
-
-
this is now the second book I've seen with a chapter dependency graph
-
New conversation -
-
-
This goes against the current ML thinking, which is that bugs in your code are just regularizers (I've actually been meaning to test this out by applying random mutations to NN learning programs)
-
well if we defined a fitness function, and selected the fittest buggy implementations from each generation...
End of conversation
New conversation -
-
-
I'm intrigued, what book/paper is this from? (Is it the same one with the dodgey i and j subscripts?)
-
old (first?) bptt paper ftp://143.54.11.3/pub/SIA/refer%C3%AAncias/BPTT.pdf
End of conversation
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.