News for hackers. Stuff that matters.
Re:Implementing Neural Turing Machines by YorkshireSeason on Thursday July 26, 2018 @03:54AM (#17615807)
Important and unsurprising sentence from the paper's abstract: "A number of open source implementations of NTMs exist but are unstable during training and/or fail to replicate the reported performance of NTMs"
Re:Implementing Neural Turing Machines by simias on Thursday July 26, 2018 @04:14AM (#17615877)
Why do you deem it unsurprising? Do you think that the opensource neural network implementations are subpar?
Re:Implementing Neural Turing Machines by YorkshireSeason on Thursday July 26, 2018 @04:17AM (#17615895)
Anecdotally: I've tried to replicate some recent AI/ML papers and failed. So have some of my acquaintances.
Re:Implementing Neural Turing Machines by nickpsecurity on Thursday July 26, 2018 @10:12AM (#17617657)
Some have written about a "reproducibility crisis" in machine learning research:

https://petewarden.com/2018/03/19/the-machine-learning-repro...

Re:Implementing Neural Turing Machines by albertzeyer on Thursday July 26, 2018 @04:24AM (#17615916)
I would expect that it was just as unstable for DeepMind. But they can automatically run lots of experiments with different hyper params so that is less an issue for them.