In plain words: A neural network is hooked up to an external memory it can read and write, like a computer's, and the whole setup is trained so it learns what to store and retrieve. From just input-output examples, it figured out simple algorithms like copying, sorting, and recalling, which ordinary networks cannot do.
Abstract · Neural Turing Machines
We extend the capabilities of neural networks by coupling them to external memory resources, which they can interact with by attentional processes. The combined system is analogous to a Turing Machine or Von Neumann architecture but is differentiable end-to-end, allowing it to be efficiently trained with gradient descent. Preliminary results demonstrate that Neural Turing Machines can infer simple algorithms such as copying, sorting, and associative recall from input and output examples.
Alex Graves, Greg Wayne, Ivo Danihelka
arXiv:1410.5401 · cs.NE · submitted Oct 20, 2014 · updated Dec 10, 2014
abstract · pdf · html
The advantage is immediate: One gets a plain website with the abstract, which allows the visitor to decide whether the PDF download is worth it. The PDF itself is only one more click away.
I personally would also leave out the v1, as that link automatically goes to the latest version in all cases.