Differentiable neural computer

This attention span allows the user to feed complex data structures such as graphs sequentially, and recall them for later use.

The researchers who published the method see promise that DNCs can be trained to perform complex, structured tasks[1][2] and address big-data applications that require some sort of reasoning, such as generating video commentaries or semantic text analysis.

On graph traversal and sequence-processing tasks with supervised learning, DNCs performed better than alternatives such as long short-term memory or a neural turing machine.

This structure allows DNCs to be more robust and abstract than a NTM, and still perform tasks that have longer-term dependencies than some predecessors such as Long Short Term Memory (LSTM).

[3][6][7] The DNC model is similar to the Von Neumann architecture, and because of the resizability of memory, it is Turing complete.

A differentiable neural computer being trained to store and recall dense binary numbers. Performance of a reference task during training shown. Upper left: the input (red) and target (blue), as 5-bit words and a 1 bit interrupt signal. Upper right: the model's output.
DNC system diagram