A Neural Turing Machine is a recurrent neural network architecture coupled with an external differentiable memory system. It combines neural pattern learning with memory access mechanisms, allowing the model to learn simple algorithmic behaviors such as copying, sorting, and associative recall from examples.
A recurrent neural network model. NTMs combine the fuzzy pattern matching capabilities of neural networks with the algorithmic power of programmable computers. An NTM has a neural network controller coupled to external memory resources, which it interacts with through attentional mechanisms. The memory interactions are differentiable end-to-end, making it possible to optimize them using gradient descent. An NTM with a long short-term memory (LSTM) network controller can infer simple algorithms such as copying, sorting, and associative recall from examples alone.