Implementing Neural Turing Machines · HackerPapers discussions

Implementing Neural Turing Machines — mentioned by MrEldritch

Wed, 01 Aug 2018 00:36:01 GMT

I know this is a big issue in AI/ML right now. Deepmind's papers are notoriously hard to reproduce, because they will lay out the general terms of the architecture but not specific implementation details - things like filter length, stride, number of layers, number of hidden units, feature selection, and all the little tricks of initialization or normalization or a zillion other subtleties. The trouble being that those "specific implementation details" are typically non-obvious and absolutely crucial to getting the system described to work at all. For instance, as far as I know, nobody's…

Paper and discussion history. A mention is not an endorsement.

Implementing Neural Turing Machines — mentioned by orbifold

Thu, 26 Jul 2018 09:27:08 GMT

The author states in his github repository (https://github.com/MarkPKCollier/NeuralTuringMachine) that his work is based on (https://github.com/snowkylin/ntm). If that is the case then I find it kind of strange that he has relicensed the work to MIT from LGPL3 and removed any reference to the original author in the LICENSE. LGPL3 requires any derivative work to be licensed the same and retain mentions of the authors, more over it also requires a clear explanation of the modifications that were undertaken. Also compared to the open source implementation (https://github.com/snowkylin/ntm) it…

Paper and discussion history. A mention is not an endorsement.

Implementing Neural Turing Machines — HN submission

Wed, 25 Jul 2018 04:44:34 GMT

Implementing Neural Turing Machines

117 points; 15 discussion replies on HN. Paper and source history. A submission is not an endorsement.