Deepmind Applies AI to Navigate The London Underground


An artificial intelligence algorithm has been developed by Google’s DeepMind that is capable of working out the most efficient way of getting from one point to another on London’s Tube network.

The system, known as a differentiable neural computer (DNC), is able to combine basic reasoning with memory in a unique way to solve such problems.

“Like a conventional computer, it can use its memory to represent and manipulate complex data structures, but, like a neural network, it can learn to do so from the data,” states a paper that details the DNC in the journal Nature.

“We show that it can learn tasks, such as finding the shortest path between specified points and inferring the missing links in randomly generated graphs, and then generalize these tasks to specific graphs, such as transport networks and family trees.”

Read the source article at Newsweek