Newsweek reports that the system used, better known as a ‘differentiable neural computer’ (DNC), combines basic reasoning with memory to solve potential issues in a unique way.
In a paper issued by Nature, the details of DNC is explained more in-depth, saying: “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”
“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 generalise these tasks to specific graphs, such as transport networks and family trees.”
This project is one of many that Google have assisted over this year, and Google’s dedication to AI it has gained international media attention for its application of AI in various industries.
Hopefully this is only the beginning of AI contributing to the public transport in London, and it will be interesting to follow the development in the future.
This article has been reproduced from: http://europe.newsweek.com/artificial-intelligence-navigates-london-underground-509405?rm=eu