A neural network architecture that can learn to perform complex tasks by reading and writing to an external memory. The NTM is a generalization of the long short-term memory (LSTM) network, which is a type of recurrent neural network (RNN).
An NTM was used to solve a problem in natural language processing by reading a database of text and using the information to generate new text. The NTM was able to learn to perform this task without being explicitly programmed to do so.