News for hackers. Stuff that matters.

A comment on The Unreasonable Effectiveness of Recurrent Neural Networks. Parent comment

Re:The Unreasonable Effectiveness of Recurrent Neural Networks by tormeh on Thursday May 21, 2015 @08:35PM (#9586107)
I meant that the state vector has constant size and just setting it at the maximum available might give you problems with training.
[ Parent | on HN ]
Re:The Unreasonable Effectiveness of Recurrent Neural Networks by varelse on Friday May 22, 2015 @02:26PM (#9590087)
Nothing you can't work around if you're willing to roll your own code. That said, I agree 100% if you're dependent on someone else's framework...
[ Parent | on HN ]