QUOTE(dreamer101 @ Jul 6 2009, 10:31 AM)
Folks,
Are you thinking like as SCIENTIST or ENGINEER??
A) SCIENTIST
This does not pass the TURING test. Hence, this is NOT AI.
B) ENGINEER
What can I use this for?? Who cares if this is not 100% AI??
Dreamer
lol, i like this post. B) FTW!
anyway, instead of focusing on how complex/fast we can get a single AI unit to be, why add up multiple albeit simpler units. Bah, i suck at putting my thoughts in coherent words. here:
» Click to show Spoiler - click again to hide... «
LEARNING FROM ANTS
To understand what Adams means by “complex behaviors,” consider how some species of ants find the shortest route to food. When a randomly foraging ant finds food, it grabs a piece and wanders back to the nest, leaving a trail of pheromones behind. Other ants set out from the nest, following that pheromone trail to seek provisions. At first, they follow it readily because the scent is recent and strong. Further away, though, pheromones have begun to evaporate, and the ants begin to wander from the trail. The ants that find the most direct route to the food and back leave the strongest scent, and their trail is the easiest to follow.
At the highest level, this looks like rational behavior. Yet it derives from very simple instincts: walk randomly until you find food, bring the food back to the nest, follow the strongest scent back to food, and repeat. Those rudimentary instincts, combined (or layered), produce complex, problem-solving behaviors.
Rodney Brooks, a researcher at the Massachusetts Institute of Technology and a co-founder of iRobot, based in Bedford, Mass., paid close attention to biological systems as potential models for robot behavior. “It was the launching point for his robots,” said Adams, who spent seven years in Brooks’ laboratory. “Up until then, researchers thought robotic intelligence meant building complex models of the world that the robot would act upon. But if you look at animals, they’re not doing that type of modeling.”
From Simple Rules, Complex BehaviourAdd the conclusions generated from the trial & error by the simple units, and whala, a reasonable learning mechanism. Sort of like getting 10 ppl with IQ of 20, 10 x 20 = 200 IQ, genius!!!
It'll be really ineffecient, but hey, someone wanted their super maybe sentient AI.
This post has been edited by ngwinnie: Aug 1 2009, 12:59 AM