Neural Algorithmic Reasoning
Algorithms have been fundamental to recent global technological advances and, in particular, they have been the cornerstone of technical advances in one field rapidly being applied to another. We argue that algorithms possess fundamentally different qualities to deep learning methods, and this strongly suggests that, were deep learning methods better able to mimic algorithms, generalisation of the sort seen with algorithms would become possible with deep learning---something far out of the reach of current machine learning methods. In fact, another advantage is that by learning algorithms, they can be adapted to the real-world problem under consideration, and may find more efficient and pragmatic solutions than those proposed by human computer scientists.
Here we present neural algorithmic reasoning---the art of building neural networks that are able to execute one or more algorithms at will---and provide our opinion on its potentially transformative potential for running classical algorithms on inputs previously considered inaccessible to them.