News for hackers. Stuff that matters.
Re:Implementing Neural Turing Machines by a_d on Thursday July 26, 2018 @03:04AM (#17615585)
“how the memory contents of a NTM are initialized may be a defining factor in the success of a NTM implementation”

Does it mean that one can expect better explainability in the future from these models?

Re:Implementing Neural Turing Machines by albertzeyer on Thursday July 26, 2018 @04:27AM (#17615930)
The result was that constant/zero initialization was the best, which is the most natural choice anyway (for me at least), and definitely also the most simple option. I'm a bit surprised that they emphasise so much on that. Also, not really sure what to learn from this.
Re:Implementing Neural Turing Machines by stochastic_monk on Thursday July 26, 2018 @06:36AM (#17616387)
Does this correspond to an intuition that a tabula rasa may be the best way for a learner to start?