Lecture 8: Semantic Networks and Frames
ฝัง
- เผยแพร่เมื่อ 25 ก.ค. 2024
- This lecture is part of the course “Foundations of Artificial Intelligence” developed by Dr. Ryan Urbanowicz in 2020 at the University of Pennsylvania’s Perelman School of Medicine. This is the first of three courses covering topics in artificial intelligence for application within the context of informatics and biomedical research. The course is divided into modules that cover (1) introductory/background materials, (2) logic, (3) other knowledge representation, (4) essentials of expert systems, (5) search, (6) uncertainty, and (7) advanced/auxiliary topics. These topics offer a global foundation for branches of AI application and research, including concepts that will later support a deeper understanding of inductive reasoning and machine learning. In a practical sense, this course focuses on how biomedical data can be organized, represented, interpreted, searched, and applied in order to derive knowledge, make decisions, and ultimately make predictions while avoiding bias.
This course was assembled using content from a wide variety of textbooks, slides, and lectures by various authors and speakers on the relevant topics. Some lectures were prepared and given by guest lecturers and thus have not been posted. At the time of posting, this course is in its second year so any feedback is welcome regarding any mistakes or suggested improvements.
Weblinks:
ryanurbanowicz.com/
www.med.upenn.edu/urbslab/
github.com/UrbsLab
Chapters:
0:00 Introduction
5:17 Semantic Networks
9:02 AND/OR Trees
10:15 IS/A Hierarchy
11:16 IS/Part Hierarchy
11:55 Inference Through Inheritance
13:34 More General Semantic Networks
18:48 Intersection Search
20:01 Tangled Hierarchies
24:06 Semantic Networks: Advantages
24:59 Semantic Networks: Disadvantages
26:30 Semantic Network Examples
32:15 From Semantic Networks to Frames
33:04 Frames
37:21 Converting Between Networks and Frames
38:07 Frames: Simple and Beyond
38:38 More on Slots
40:04 More on Frames
44:04 Advantages of Frames
45:03 Disadvantages of Frames
45:55 Frame Examples
46:45 Scripts
49:39 Other Semantic Network Related Representations
52:12 Conclusion
you are sir one hell of a professor. thank you for these lectures
very helpfull and informational, thank you!
Thanks for uploading, great content!
Sir, you are an amazing lecturer
Thank you kindly for the compliment
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?
thanks for your hard work
It's my pleasure
Are semantic networks also known as knowledge graphs?
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.
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!
6:40
wow. this is what I have been creating professionally for 25 years, without knowing what it was called. 😅