Course Overview
description
Transcript of Course Overview
![Page 1: Course Overview](https://reader035.fdocuments.in/reader035/viewer/2022062409/56814fbf550346895dbd779a/html5/thumbnails/1.jpg)
Course OverviewWhat is AI?
What are the Major Challenges?
What are the Main Techniques?
Where are we failing, and why?
Step back and look at the Science
Step back and look at the History of AI
What are the Major Schools of Thought?
What of the Future?
Done
Done
![Page 2: Course Overview](https://reader035.fdocuments.in/reader035/viewer/2022062409/56814fbf550346895dbd779a/html5/thumbnails/2.jpg)
Course Overview What is AI?
What are the Major Challenges?
What are the Main Techniques? (How do we do it?)
Where are we failing, and why?
Step back and look at the Science
Step back and look at the History of AI
What are the Major Schools of Thought?
What of the Future?
![Page 3: Course Overview](https://reader035.fdocuments.in/reader035/viewer/2022062409/56814fbf550346895dbd779a/html5/thumbnails/3.jpg)
Course Overview What is AI?
What are the Major Challenges?
What are the Main Techniques? (How do we do it?)
Where are we failing, and why?
Step back and look at the Science
Step back and look at the History of AI
What are the Major Schools of Thought?
What of the Future?
Search Logics (knowledge representation and reasoning) Planning Bayesian belief networks Neural networks Evolutionary computation Reinforcement learning
![Page 4: Course Overview](https://reader035.fdocuments.in/reader035/viewer/2022062409/56814fbf550346895dbd779a/html5/thumbnails/4.jpg)
Course Overview What is AI?
What are the Major Challenges?
What are the Main Techniques? (How do we do it?)
Where are we failing, and why?
Step back and look at the Science
Step back and look at the History of AI
What are the Major Schools of Thought?
What of the Future?
Search Logics (knowledge representation and reasoning) Planning Bayesian belief networks Neural networks Evolutionary computation Reinforcement learning
![Page 5: Course Overview](https://reader035.fdocuments.in/reader035/viewer/2022062409/56814fbf550346895dbd779a/html5/thumbnails/5.jpg)
Course Overview What is AI?
What are the Major Challenges?
What are the Main Techniques? (How do we do it?)
Where are we failing, and why?
Step back and look at the Science
Step back and look at the History of AI
What are the Major Schools of Thought?
What of the Future?
Search Logics (knowledge representation and reasoning) Planning Bayesian belief networks Neural networks Evolutionary computation Reinforcement learning
These are all in fact types of
“Machine Learning”
![Page 6: Course Overview](https://reader035.fdocuments.in/reader035/viewer/2022062409/56814fbf550346895dbd779a/html5/thumbnails/6.jpg)
Dealing with Uncertainty The need to deal with uncertainty arose in “expert systems”
Code expertise into a computer systemExample: Medical diagnosis: MYCIN Equipment failure diagnosis in a factory
Sample from MYCIN: IF
The infection is primary-bacteremia AND The site of the culture is one of the sterile sites AND The suspected portal of entry is the gastrointestinal tract
THEN There is suggestive evidence (70%) that the infection is bacteroid
Expert systems often have long chains IF X THEN Y … IF Y THEN Z … IF Z THEN W … If uncertainty is not handled correctly, errors build up, wrong diagnosis Also, there may be dependencies, e.g. X and Y depend on each other Leads to more errors…
Need a proper way to deal with uncertainty
![Page 7: Course Overview](https://reader035.fdocuments.in/reader035/viewer/2022062409/56814fbf550346895dbd779a/html5/thumbnails/7.jpg)
How do Humans Deal with Uncertainty? Not very well…
Consider a form of cancer which afflicts 0.8% of people (rare) A lab has a test to detect the cancer The test has a 98% chance to give an accurate result Mr. Bloggs goes for the test
The result comes back positive i.e. the test says he has cancer
What is the chance that he has the cancer? 28%
Afflicts experts too Studies have shown: human experts thinking of likelihoods do not reason
like mathematical probability
![Page 8: Course Overview](https://reader035.fdocuments.in/reader035/viewer/2022062409/56814fbf550346895dbd779a/html5/thumbnails/8.jpg)
A
B C
D E
Increased total serum count
Metastatic cancer
Brain Tumour
Severe headachesComa
![Page 9: Course Overview](https://reader035.fdocuments.in/reader035/viewer/2022062409/56814fbf550346895dbd779a/html5/thumbnails/9.jpg)
A
B C
D E
Increased total serum count
Metastatic cancer
Brain Tumour
Severe headachesComa
No Link
![Page 10: Course Overview](https://reader035.fdocuments.in/reader035/viewer/2022062409/56814fbf550346895dbd779a/html5/thumbnails/10.jpg)
A
B C
D E
Increased total serum count
Metastatic cancer
Brain Tumour
Severe headachesComa
Serum count
Brain tumour
Coma
Yes Yes 95%
Yes No 94%
No Yes 29%
No No 0.1%
![Page 11: Course Overview](https://reader035.fdocuments.in/reader035/viewer/2022062409/56814fbf550346895dbd779a/html5/thumbnails/11.jpg)
A
B C
D E
Increased total serum count
Metastatic cancer
Brain Tumour
Severe headachesComa
Serum count
Brain tumour
Coma
Yes Yes 95%
Yes No 94%
No Yes 29%
No No 0.1%
Brain tumour
headache
Yes 70%
No 1%
![Page 12: Course Overview](https://reader035.fdocuments.in/reader035/viewer/2022062409/56814fbf550346895dbd779a/html5/thumbnails/12.jpg)
A
B C
D E
Increased total serum count
Metastatic cancer
Brain Tumour
Severe headachesComa
Serum count
Brain tumour
Coma
Yes Yes 95%
Yes No 94%
No Yes 29%
No No 0.1%
Brain tumour
headache
Yes 70%
No 1%
… …
… …
… …
… …
… …
… …
… …
… …
… …
![Page 13: Course Overview](https://reader035.fdocuments.in/reader035/viewer/2022062409/56814fbf550346895dbd779a/html5/thumbnails/13.jpg)
Inference in Belief Networks Questions for a belief network:
Diagnosis Work backwards from some evidence to a hypothesis
Causality Work forwards from some hypothesis to likely evidence Test a hypothesis, find likely symptoms
In general – mixed mode Give values for some evidence variables Ask about values of others
No other approach handles all these modes
Reasoning can take some time Need to be careful to design network Local structure: few connections
![Page 14: Course Overview](https://reader035.fdocuments.in/reader035/viewer/2022062409/56814fbf550346895dbd779a/html5/thumbnails/14.jpg)
How Good are Belief Networks? Relieves you from coding all possible dependencies
How many possibilities if full network?
Tools are available Build network graphically System handles mathematical probabilities
Case study: Pathfinder a medical expert system
Assists pathologists with diagnosis of lymph-node diseases Pathfinder is a pun
User enters initial findings Pathfinder lists possible diseases User can
Enter more findings Ask pathfinder which findings would narrow possibilities
Pathfinder refines the diagnosis Pathfinder version based on Belief Networks performs significantly better
than human pathologists
![Page 15: Course Overview](https://reader035.fdocuments.in/reader035/viewer/2022062409/56814fbf550346895dbd779a/html5/thumbnails/15.jpg)
QUIZ
![Page 16: Course Overview](https://reader035.fdocuments.in/reader035/viewer/2022062409/56814fbf550346895dbd779a/html5/thumbnails/16.jpg)
“Machines will be capable,
within _____ years,
of doing any work that a man can do.”
Herbert Simon, 1965.
![Page 17: Course Overview](https://reader035.fdocuments.in/reader035/viewer/2022062409/56814fbf550346895dbd779a/html5/thumbnails/17.jpg)
What disciplines are considered as sub-areas of Cognitive Science?
![Page 18: Course Overview](https://reader035.fdocuments.in/reader035/viewer/2022062409/56814fbf550346895dbd779a/html5/thumbnails/18.jpg)
1966: “Any task that requires real understanding of natural language is
too difficult for a computer” - Bar-Hillel
![Page 19: Course Overview](https://reader035.fdocuments.in/reader035/viewer/2022062409/56814fbf550346895dbd779a/html5/thumbnails/19.jpg)
Time flies like an arrow.
![Page 20: Course Overview](https://reader035.fdocuments.in/reader035/viewer/2022062409/56814fbf550346895dbd779a/html5/thumbnails/20.jpg)
Give an example which shows why speech recognition is hard for computers.
![Page 21: Course Overview](https://reader035.fdocuments.in/reader035/viewer/2022062409/56814fbf550346895dbd779a/html5/thumbnails/21.jpg)
Major tasks in robotics:
1. Localisation/mapping Range finders Landmarks Always uncertainty
2. ?
![Page 22: Course Overview](https://reader035.fdocuments.in/reader035/viewer/2022062409/56814fbf550346895dbd779a/html5/thumbnails/22.jpg)
DARPA Grand Challenge 2004
150-mile route in Mojave Desert (off-road course)
Best performance? (require accuracy to nearest 2 miles)
![Page 23: Course Overview](https://reader035.fdocuments.in/reader035/viewer/2022062409/56814fbf550346895dbd779a/html5/thumbnails/23.jpg)
Vision Hierarchy
4. High level Models
3. Mid level ????
2. Putting together Multiple images
1. Low level processing on a single image
0. The physics of image formation
![Page 24: Course Overview](https://reader035.fdocuments.in/reader035/viewer/2022062409/56814fbf550346895dbd779a/html5/thumbnails/24.jpg)
Go (Wei Qi)Humans don’t want to play computers because ?
![Page 25: Course Overview](https://reader035.fdocuments.in/reader035/viewer/2022062409/56814fbf550346895dbd779a/html5/thumbnails/25.jpg)
John McCarthy, "Programs with Common
Sense", 1958.
"Our ultimate objective is to make "Our ultimate objective is to make programs that learn from their programs that learn from their
experience as effectively as humans experience as effectively as humans do. We shall…say that a program do. We shall…say that a program
has common sense if ?”has common sense if ?”
![Page 26: Course Overview](https://reader035.fdocuments.in/reader035/viewer/2022062409/56814fbf550346895dbd779a/html5/thumbnails/26.jpg)
DefenceA big user of AI.
"... the deployment of a single ??????
called DART during the Desert Shield/Storm Campaign paid back all US government investment in AI/KBS research over a 30 year
period."
Tate A. Smart Planning. ARPI Proc. 1996.
![Page 27: Course Overview](https://reader035.fdocuments.in/reader035/viewer/2022062409/56814fbf550346895dbd779a/html5/thumbnails/27.jpg)
Can use logic to represent a hierarchy of concepts isa(Tweety, canary) isa(canary, bird) isa(bird, animal) isa(animal, living_thing) isa(living_thing, physical_thing) isa(physical_thing, tangible_thing) isa(tangible_thing, thing)
What do we call this?
![Page 28: Course Overview](https://reader035.fdocuments.in/reader035/viewer/2022062409/56814fbf550346895dbd779a/html5/thumbnails/28.jpg)
“Machines will be capable,
within _____ years,
of doing any work that a man can do.”
Herbert Simon, 1965.
![Page 29: Course Overview](https://reader035.fdocuments.in/reader035/viewer/2022062409/56814fbf550346895dbd779a/html5/thumbnails/29.jpg)
“Machines will be capable,
within twenty years,
of doing any work that a man can do.”
Herbert Simon, 1965.
![Page 30: Course Overview](https://reader035.fdocuments.in/reader035/viewer/2022062409/56814fbf550346895dbd779a/html5/thumbnails/30.jpg)
What disciplines are considered as sub-areas of Cognitive Science?
![Page 31: Course Overview](https://reader035.fdocuments.in/reader035/viewer/2022062409/56814fbf550346895dbd779a/html5/thumbnails/31.jpg)
What disciplines are considered as sub-areas of Cognitive Science?
Cognitive Science
Psychology
Philosophy
Neuroscience
Artificial Intelligence
Linguistics
Anthropology
![Page 32: Course Overview](https://reader035.fdocuments.in/reader035/viewer/2022062409/56814fbf550346895dbd779a/html5/thumbnails/32.jpg)
1966: “Any task that requires real understanding of natural language is
too difficult for a computer” - Bar-Hillel
![Page 33: Course Overview](https://reader035.fdocuments.in/reader035/viewer/2022062409/56814fbf550346895dbd779a/html5/thumbnails/33.jpg)
1966: “Any task that requires real understanding of natural language is
too difficult for a computer” - Bar-Hillel
![Page 34: Course Overview](https://reader035.fdocuments.in/reader035/viewer/2022062409/56814fbf550346895dbd779a/html5/thumbnails/34.jpg)
Time flies like an arrow.
![Page 35: Course Overview](https://reader035.fdocuments.in/reader035/viewer/2022062409/56814fbf550346895dbd779a/html5/thumbnails/35.jpg)
Time flies like an arrow.
(You should) time flies as you would (time) an arrow
Time flies in the same way that an arrow would (time them)
Time those flies that are like arrows
Fruit flies like a banana
each of above
Time magazine travels straight when thrown
![Page 36: Course Overview](https://reader035.fdocuments.in/reader035/viewer/2022062409/56814fbf550346895dbd779a/html5/thumbnails/36.jpg)
Give an example which shows why speech recognition is hard for computers.
![Page 37: Course Overview](https://reader035.fdocuments.in/reader035/viewer/2022062409/56814fbf550346895dbd779a/html5/thumbnails/37.jpg)
Give an example which shows why speech recognition is hard for computers.
“eat I scream” vs. “eat ice cream”
![Page 38: Course Overview](https://reader035.fdocuments.in/reader035/viewer/2022062409/56814fbf550346895dbd779a/html5/thumbnails/38.jpg)
Major tasks in robotics:
1. Localisation/mapping Range finders Landmarks Always uncertainty
2. ?
![Page 39: Course Overview](https://reader035.fdocuments.in/reader035/viewer/2022062409/56814fbf550346895dbd779a/html5/thumbnails/39.jpg)
Major tasks in robotics:
1. Localisation/mapping Range finders Landmarks Always uncertainty
2. Motion planning For body location in world For arms/fingers
![Page 40: Course Overview](https://reader035.fdocuments.in/reader035/viewer/2022062409/56814fbf550346895dbd779a/html5/thumbnails/40.jpg)
DARPA Grand Challenge 2004
150-mile route in Mojave Desert (off-road course)
Best performance? (require accuracy to nearest 2 miles)
![Page 41: Course Overview](https://reader035.fdocuments.in/reader035/viewer/2022062409/56814fbf550346895dbd779a/html5/thumbnails/41.jpg)
DARPA Grand Challenge 2004
150-mile route in Mojave Desert (off-road course)
Best performance: 7.36 miles
![Page 42: Course Overview](https://reader035.fdocuments.in/reader035/viewer/2022062409/56814fbf550346895dbd779a/html5/thumbnails/42.jpg)
Vision Hierarchy
4. High level Models
3. Mid level ????
2. Putting together Multiple images
1. Low level processing on a single image
0. The physics of image formation
![Page 43: Course Overview](https://reader035.fdocuments.in/reader035/viewer/2022062409/56814fbf550346895dbd779a/html5/thumbnails/43.jpg)
Vision Hierarchy
4. High level Models
3. Mid level Segmentation
2. Putting together Multiple images
1. Low level processing on a single image
0. The physics of image formation
![Page 44: Course Overview](https://reader035.fdocuments.in/reader035/viewer/2022062409/56814fbf550346895dbd779a/html5/thumbnails/44.jpg)
Go (Wei Qi)Humans don’t want to play computers because ?
![Page 45: Course Overview](https://reader035.fdocuments.in/reader035/viewer/2022062409/56814fbf550346895dbd779a/html5/thumbnails/45.jpg)
Go (Wei Qi)Humans don’t want to play computers because computers are too bad
![Page 46: Course Overview](https://reader035.fdocuments.in/reader035/viewer/2022062409/56814fbf550346895dbd779a/html5/thumbnails/46.jpg)
John McCarthy, "Programs with Common
Sense", 1958.
"Our ultimate objective is to make "Our ultimate objective is to make programs that learn from their programs that learn from their
experience as effectively as humans experience as effectively as humans do. We shall…say that a program do. We shall…say that a program
has common sense if ?”has common sense if ?”
![Page 47: Course Overview](https://reader035.fdocuments.in/reader035/viewer/2022062409/56814fbf550346895dbd779a/html5/thumbnails/47.jpg)
John McCarthy, "Programs with Common
Sense", 1958.
"Our ultimate objective is to make "Our ultimate objective is to make programs that learn from their programs that learn from their
experience as effectively as humans experience as effectively as humans do. We shall…say that a program do. We shall…say that a program
has common sense if it has common sense if it automatically deduces for itself a automatically deduces for itself a sufficient wide class of immediate sufficient wide class of immediate consequences of anything it is told consequences of anything it is told
and what it already knows.”and what it already knows.”
![Page 48: Course Overview](https://reader035.fdocuments.in/reader035/viewer/2022062409/56814fbf550346895dbd779a/html5/thumbnails/48.jpg)
DefenceA big user of AI.
"... the deployment of a single ??????
called DART during the Desert Shield/Storm Campaign paid back all US government investment in AI/KBS research over a 30 year
period."
Tate A. Smart Planning. ARPI Proc. 1996.
![Page 49: Course Overview](https://reader035.fdocuments.in/reader035/viewer/2022062409/56814fbf550346895dbd779a/html5/thumbnails/49.jpg)
DefenceA big user of AI.
"... the deployment of a single logistics support aid called DART during the Desert Shield/Storm
Campaign paid back all US government investment in AI/KBS research over a 30 year period."
Tate A. Smart Planning. ARPI Proc. 1996.
![Page 50: Course Overview](https://reader035.fdocuments.in/reader035/viewer/2022062409/56814fbf550346895dbd779a/html5/thumbnails/50.jpg)
Can use logic to represent a hierarchy of concepts isa(Tweety, canary) isa(canary, bird) isa(bird, animal) isa(animal, living_thing) isa(living_thing, physical_thing) isa(physical_thing, tangible_thing) isa(tangible_thing, thing)
What do we call this?
![Page 51: Course Overview](https://reader035.fdocuments.in/reader035/viewer/2022062409/56814fbf550346895dbd779a/html5/thumbnails/51.jpg)
Can use logic to represent a hierarchy of concepts isa(Tweety, canary) isa(canary, bird) isa(bird, animal) isa(animal, living_thing) isa(living_thing, physical_thing) isa(physical_thing, tangible_thing) isa(tangible_thing, thing)
What do we call this? Ontology