--- "Dr. Matthias Heger" <[EMAIL PROTECTED]> wrote: > >>>>>>>>Matt Mahoney [mailto:[EMAIL PROTECTED] > > Repeat the trial many times. Out of the thousands of perceptual > features present when the child hears "ball", the relevant features > will reinforce and the others will cancel out. > > The concept of "ball" that a child learns is far too complex to > manually code into a structured knowledge base. An orange is round > but > not a ball. An American football is not round. Knowing that a ball > is a sphere does not help an AI viewing a small video of a tennis or > badminton match know that the single yellow pixel moving across the > image is a ball but the white pixel is not. > > <<<<<<<<<<<< > > I agree. But it is difficult to believe that the relevant features > simply > reinforce out of the thousands by seeing a ball several times. > Trials with > artificial neural networks could learn some patterns but failed to > get the idea of complex objects.
A child does not need to get the idea in the sense that you would program a concise definition into a knowledge base. A child can recognize a ball more accurately than any AI we have built, without any concept of "radius" or "sphere" or even "solid" or "object". > > >>>>>>>>>>-- Matt Mahoney wrote > The retina uses low level feature detection of spots, edges, and > movement to compress 137 million pixels down to 1 million optic nerve > fibers. By the time it gets through the more complex feature > detectors of the visual cortex and into long term memory, it has been > compressed down to 2 bits per second. > <<<<<<<<<<<<<< > > If we know how this compression works we have solved one of the main > problems of AGI. > This process is partially learned and here we must find out what we > learn and what is coded from the first day. > I could imagine that a baby brain gets less bits/ seconds and learns > basic patterns during the first weeks. Then, the eyes and the retina > changes. > Using the learned patterns the brain can later handle the huge amount > of bits from the eyes. A child must learn to see before being able to recognize a ball. Recognizing the lower level features like lines, edges, corners, and shapes is a (bottom up series of) unsupervised clustering algorithms which can be solved efficiently using neural networks. We know such features are learned because kittens blind in one eye do not develop those feature detectors for that eye. Kittens raised in rooms with vertical stripes develop detectors for only vertical lines and edges. -- Matt Mahoney, [EMAIL PROTECTED] ------------------------------------------- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244&id_secret=101455710-f059c4 Powered by Listbox: http://www.listbox.com
