This stuff in the video is symbolic AI, where Boolean logic and inferencing rules like modus ponens are used to derive new knowledge. This methodology is based on what is called the Physical Symbol System hypothesis (states that processing structures of symbols is sufficient, in principle, to produce artificial intelligence in a digital computer). Neural networks are sub-symbolic statistical pattern recognition machines that represent learned knowledge as patterns of activation across many simple computing elements. So there is no specific location in the network for "grandmother" which would be distributed among many thousands of nodes, where it has seen many thousands of examples of people and their relationships. In a logic system grandmother of X might look like: grandmother(X) :- mother(mother(X)),mother(father(X)), ie a grandmother is your mother or father's mother. Any mother that is the mother of either the mother or father or X is their grandmother. Hope this helps; corrections welcome.
2 года назад
For example, I want to create a semantic content network in the category of ring weapons in my game blog. how can I do that?
you are sir one hell of a professor. thank you for these lectures
Sir, you are an amazing lecturer
Thank you kindly for the compliment
Thanks for uploading, great content!
sir, 40:09 did you mean to say Predicate Logic (instead of Propositional Logic)?
Yes, i did mean to say Predicate Logic, thanks for the catch!
very helpfull and informational, thank you!
I had One question? How does this sematic networks and frames helps to create neural network to solve real world problems.
This stuff in the video is symbolic AI, where Boolean logic and inferencing rules like modus ponens are used to derive new knowledge. This methodology is based on what is called the Physical Symbol System hypothesis (states that processing structures of symbols is sufficient, in principle, to produce artificial intelligence in a digital computer). Neural networks are sub-symbolic statistical pattern recognition machines that represent learned knowledge as patterns of activation across many simple computing elements. So there is no specific location in the network for "grandmother" which would be distributed among many thousands of nodes, where it has seen many thousands of examples of people and their relationships. In a logic system grandmother of X might look like: grandmother(X) :- mother(mother(X)),mother(father(X)), ie a grandmother is your mother or father's mother. Any mother that is the mother of either the mother or father or X is their grandmother. Hope this helps; corrections welcome.
For example, I want to create a semantic content network in the category of ring weapons in my game blog. how can I do that?
Are semantic networks also known as knowledge graphs?
thanks for your hard work
It's my pleasure
6:40
wow. this is what I have been creating professionally for 25 years, without knowing what it was called. 😅