… “What makes it messy is the presence of different possibilities," Barthelemy says. "When you arrive at a specific point, you have many choices."
The Paris system has 78 such choice points. The New York subway, the most complex in the world, has 161. New York's system is so sprawling and interconnected, Barthelemy and colleagues Riccardo Gallotti and Mason Porter concluded in a recent analysis, that it approaches the maximum complexity our human minds can handle, the equivalent of about 8 bits of information.
“But then if you add the bus,” Barthelemy warns, “the 8-bit limit is exploded."...
What is the best way to get from A to B by public transit? Google Maps is answering such queries for over 20,000 cities and towns in over 70 countries around the world, including large metro areas like New York, São Paulo or Moscow…
… Scalable Transfer Patterns algorithm  does just that, but in a smart way. For starters, it uses what is known as graph clustering to cut the network into pieces, called clusters, that have a lot of connections inside but relatively few to the outside…
… Frequency-Based Search for Public Transit  is carefully designed to find and take advantage of repetitive schedules while representing all one-off cases exactly. Comparing to the set-up from the original Transfer Patterns paper , the authors estimate a whopping 60x acceleration of finding transfer patterns from this part alone….
Humans can’t manage modern transit complexity — but the AIs can. Including the AI in your pocket.
Everyone needs a portable AI, including people with no income and people with cognitive disabilities. That’s one reason I’m writing my smartphone for all book.