7
« Last post by LOCKSUIT on April 23, 2018, 11:53:50 pm »
Did you know vision can be sentences for discovery too? Looking at a hammer is the word hammer. Seeing a video sequence of a hammer smashing crystals is the sentence "Hammer smashing crystals." I can actually say by speech the top node sentence in ONE word - slap, faster than having to see it visually. This is because every sequence is just so you recognize 1 high-level node, and unless you're in the real world rogue, you can use symbols to say sentences by ONE word. Seeing a dinning table of soldiers guarding a pod from aliens are sentences that build up to select/create a higher-level node in a hierarchy net. But these are single images that are instantly recognized sentences (no sequence waiting time). I can speak: Guarding, which is like saying Slap, not needing a sequence to recognize a sentence. Lastly vision
Hmm, if HUGE marshmallows (their tiny core) areMadeOf crystals, glass isMadeOf crystals, windows AreMadeOf glass, and windows cost money, then, if you ask "Can hugeMarshmallows break windows?", well, it can't begin the loop/connection around BY "predicate weight" because in the case it had learned that hammers canBreak crystals - the link predicate "canBreak" is not as strong as MadeOf (Madeof is stronger yet no proof hammers can break anything). And here with the hugeMarshmallows we have a predicate link "MadeOf" to crystals which is strong but doesn't say anything about being able to break anything. Hence this example loop would loop around and wrongly conclude hugeMarshmallows canBreak windows if asked so. SO, weight forwards a connection? No... So then is it predicate NAME? I guess so.
Therefore, if hammers have not been known to canBreak anything, it can see that hammers are hard and hard things canBreak things but if nothing has been known to break, then no worky...
It needs to know the definition of what break means i.e. hard objects can break/hurt brittle and living objects.
So............You ask "Hammers canBreak windows?". Then it searches to verify this and it sees that hammers canBreak crystals. Then it looks from there, and finds glass isMadeOf crystals, great, but before it calls it a possible step forward for looping around to the question nodes, it first looks at the properties of hammer>crystals and crystals>glass for similarities. Mini discoveries supporting bigger discoveries. It can also look at the properties of crystals and windows/glass to look for commonalities.
A predicate can have a direction/arrow of flow. If one is the opposite way, it'd stop the loop from going around.
So far we got flow, mini discoveries, weights, and predicate names.
Socrates isA man, man isA mortal, therefore Socrates isA mortal. And the hammer example. Both you ask if hammers/Soctrates canBreak/isA windows/mortal. Then BOTH nodes (ex. hammer node and window node) look to see if there is any identical predicate names protruding out of themselves ex. oh, well "hammers canBreak crystals" or "windows canBreak rocks" backwards. Further, once it finds a identical predicate exists, well then if any connected literally "=" it i.e. isMadeOf, then essentially simply saying "Hammers canBreak crystals" is saying "Hammers canBreak windows".
Try making a belief self-ignite like "Hammers canBreak crystals" but when it fires make it get tweaked at the end word so it might become ex. "Hammers canBreak rocks/glasses/paper/etc". Then have it see if it can form discoveries towards a goal it desires. Also if both light up (Hammers canBreak crystals & Hammers canBreak windows), then, it can compare them to look for commonalities or look for commonalities by looking for a connection between them like we've been doing here.