A clear understanding of how the brain works will make it possible for
us to build intelligent machines, in silicon, that will exceed our human
ability in surprising ways.
The brain is not a computer, but a memory system that stores experiences
in a way that reflects the true structure of the world, remembering
sequences of events and their nested relationships and making
predictions based on those memories. It is this memory-prediction
system that forms the basis of intelligence, perception, creativity, and
even consciousness.
The neocortex is the seat of most aspects of perception and high-level
thought. I propose that the neocortex can be understood as a
hierarchical sequence memory. This talk will describe the anatomy and
physiology of the cortex, and show that they can be accurately captured
by a mathematical model based on conditional probabilities. An
implementation of this system will be shown that demonstrates robust
invariant image recognition.
Date and Time
Thursday February 3, 2005 4:00pm -
5:30pm
Location
Computer Science Small Auditorium (Room 105)
Event Type
Speaker
Jeff Hawkins, from Redwood Neuroscience Institute and PalmOne
Host
Brian Kernighan