These guys have applied stochastic computing to the process of pattern recognition. The problem here is to compare an input signal with a reference signal to determine whether they match.
In the real world, of course, input signals are always noisy so a system that can cope with noise has an obvious advantage.
Canals and co use their technique to help an autonomous vehicle navigate its way through a simple environment for which it has an internal map. For this task, it has to measure the distance to the walls around it and work out where it is on the map. It then computes a trajectory taking it to its destination.
LeopoldS on 22 Aug 12and what is your take?
Luís F. Simões on 23 Aug 12As William Gibson famously said "The future is already here - it's just not very evenly distributed." Many of the listed technologies are already here, in one way or another, the authors are just putting dates on when they think they'll achieve greater consumer impact. I have issues with many of those dates. I think there are a lot of under- and overestimations. Also, what a bleak future for AI it that's all it'll give the world in the next 30 years!
