Consider video. Humans recognize object features, like apple, stem, curve, even 
a dot. Some apples are green, some are distorted, some may look like a piano 
(almost never lol). It is the shape of a piano, and the color and texture zig 
zags of an apple, so depending on which you focus on you will notice one in 
isolation. Of course to recognize 'apple' fully will require not just texture 
and color but also shape, meaning 'apple' doesn't activate fully because it has 
the shape of a piano in our case here. But it can be sure it is most likely an 
apple for various reasons, and edible. We can recognize an apple being thrown 
as 'motion' and 'motion of apple'. Human seem to write text as they see vision, 
like I lift my arm and throw a ball to Tom. So humans will see a sequence of 
these features like apple...moving...hits wall....apple disappears....wall 
remains. And humans will remember important features like food and will talk 
about them on their own to creating related data. Humans use text as their 
gateway to say what they are thinking. Apples, motion, and shapes appear on 
Earth multiple places, there's re-occurrence. Vision can store a sequence in an 
image or a video of images. Position matters less in a single frame unless you 
pay attention to a let's say pirate map painting a trail to an X like 
a>b>c>d>X...in that case you see a sequence in a single image! However how long 
did you look at the image? Ah so it was a video, of what you saw in order. You 
always see 1 feature at a time, it may be 'apple', or 'multiple fruit', and 
when it is 'apple' it may slightly activate 'multiple fruit' if the surrounds 
seep into your attention by accident.

------------------------------------------
Artificial General Intelligence List: AGI
Permalink: 
https://agi.topicbox.com/groups/agi/T43ab26814eaa1bdd-M9b4078cce5eed1185a5d64d0
Delivery options: https://agi.topicbox.com/groups/agi/subscription

Reply via email to