Link zur Vorlesung!
About the Lecture
Talk about intelligent designs: Jeff Hawkins says he‚Äôs mapped out the way the human brain works, and has begun to fashion thinking machines to emulate the process. It comes down to Hierarchical Temporal Memory (HTM). Basically, he says, our brains take sensory inputs from the world and build a set of beliefs around the causes of those inputs. ‚ÄúDiscovering causes is the pinnacle of what brains do,‚ÄĚ says Hawkins. But getting good at this kind of ‚Äúfancy pattern recognition‚ÄĚ is something developing humans seem to do effortlessly, and computers only with immense labor. Learning to differentiate a cat and a dog, for instance, doesn‚Äôt come naturally to a computer. Hawkins layers his machine brains with nodes that make inferences about outside sensory data, and then pass these hunches on up a hierarchy of nodes until a consensus -- a belief -- evolves about the source of the data. The use of ‚Äúbelief propagation techniques‚ÄĚ, says Hawkins, enables an entire system to reach the best overall consensus swiftly. As the thinking machine develops common representations of objects or ideas, it can generalize about new data coming at it, and learn to attend only to information that matters.
When Hawkins presented an HTM vision system with primitive line drawings of a helicopter and a mug, the system learned to identify them, even when their orientations changed dramatically, and when the lines were blurred. But the program also correctly rejected chopped-up versions of the same drawings as nonsense. ‚ÄúStable beliefs at the top lead to changing predictions and behavior at the bottom,‚ÄĚ says Hawkins. Where does this lead? Possibly to ‚Äúmachines that are much smarter than humans,‚ÄĚ says Hawkins, computers whose abilities extend beyond sense biology and provide a means to expand such complex fields as weather, cosmology and genetics.