Neural Turing machine

Neural Turing machines (NTMs) combine the fuzzy pattern matching capabilities of neural networks with the algorithmic power of programmable computers. They are an extension of neural networks that are coupled to external memory resources, which they interact with through attentional mechanisms. Their memory interactions are differentiable end-to-end, making it possible to optimize them using gradient descent.[1] They can infer simple algorithms such as copying, sorting, and associative recall from input and output examples.[2]

They can infer algorithms from input and output examples alone.

Differentiable neural computers are an outgrowth of neural Turing machines, with attention mechanisms that control where the memory is active, and improved performance.[3]

See also

References

  1. ↑ "Deep Minds: An Interview with Google's Alex Graves & Koray Kavukcuoglu". Retrieved May 17, 2016.
  2. ↑ Graves, Alex; Wayne, Greg; Danihelka, Ivo (2014). "Neural Turing Machines". arXiv:1410.5401Freely accessible [cs.NE].
  3. ↑ Administrator. "DeepMind's Differentiable Neural Network Thinks Deeply". www.i-programmer.info. Retrieved 2016-10-20.
This article is issued from Wikipedia - version of the 11/24/2016. The text is available under the Creative Commons Attribution/Share Alike but additional terms may apply for the media files.