Artificial Intelligence

Spring 2023,
Lecture 1
Amir EL Ghamry
 Artificial Intelligence Example
2

Use google maps

Google
Maps
 Artificial Intelligence Example – cont…
3
 Artificial Intelligence Example – cont…
4
 Artificial Intelligence Example – cont…
5

Google maps predict whether the traffic is

Clear ,
slow moving ,
or heavily congested based on :

1- Average time taken on specific days at

specific times on that route

2- Real time location data of vehicles

from google maps and sensors
 Artificial Intelligence Example

Example of
prescriptive
analytics
Recommender systems
• Observe a behavior and
“recommend” items to buy,
music to lissen, people to
follow on social,..
Are they similar?
8
 Applications of AI
9
Predict if a person has diabetes
 Applications of AI
10
Applications of AI in smart home
Applications of AI in smart home
Consider we designed a robot in our lab and move it to the filed
New environment
Which path the robot choose. ?
What the robot do when he face difficult situation
a robot should find a solution
Characteristics of intelligent robot
W h a t is AI?
Four schools of thoughts (Russel & Norvig)

Thinking humanly Thinking rationally

“ T h e exciting new effort to make “The study of mental faculties

computers think... machines with through the use of computational

minds, in the full and literal sense.” models.” (Charniak and McDermott,
(Haugeland, 1985) 1985

Acting humanly Acting rationally

“ T h e study of how to make com- “Computational Intelligence is the

puters do things which, at the mo- study of the design of intelligent

ment, people are better.” (Rich and agents.” (Poole et al., 1998)
Knight, 1991)
 W h a t is A I?
1- Thinking humanly: cognitive approach

Requires to determine how humans think! 1960’s

“cognitive revolution”.
Requires scientific theories of internal activities of the brain
• What level of abstraction? “Knowledge” or “circuits”?
• How to validate?
Today, Cognitive Science and Artificial Intelligence are distinct
disciplines.
2-
W h a t is A I?
A cting humanly:
3-
 W h a t is A I?
4- A cting rationally:
• T he right thing: that which is expected to maximize goal
achievement, given the available information.

• A rational agent is one that acts so as to achieve the best

outcome, or when there is uncertainty, the best expected out-
come.

• Aristotle (Nicomachean Ethics):

“ E very art and every inquiry, and sim ilarly every act ion and
pursuit, is thought t o aim at some g o o d . ”
W h a t is AI?
Four schools of thoughts (Russel & Norvig)

Thinking humanly Thinking rationally

“ T h e exciting new e↵ort to make “The study of mental faculties

computers think... machines with through the use of computational
minds, in the full and literal sense.” models.” (Charniak and McDermott,
(Haugeland, 1985) 1985

Acting humanly Acting rationally: O u r approach

“ T h e study of how to make com- “Computational Intelligence is the

puters do things which, at the mo- study of the design of intelligent

ment, people are better.” (Rich and agents.” (Poole et al., 1998)
Knight, 1991)
Applications of A I
Applications of A I
Speech recognition

• Virtual assistants: Siri (Apple),

Echo (Amazon), Google Now, Cor-
tana (Microsoft).

• “ T h e y ” helps get things done: send

an email, make an appointment,
find a restaurant, tell you the
weather and more.

• Leverage deep neural networks to

handle speech recognition and
natural language understanding.
Applications of A I
Handwriting recognition (check, zipcode)
Applications of A I
Machine translation
• Historical motivation: translate Russian to English.

• First systems using mechanical translation (one-to-one cor-

respondence) failed!

• “ O u t of sight, out of mind” ) “Invisible, imbecile”.

Applications of A I
Machine translation
• Historical motivation: translate Russian to English.

• First systems using mechanical translation (one-to-one cor-

respondence) failed!

• “ O u t of sight, out of mind” ) “Invisible, imbecile”.

Oops!
Applications of A I
Machine translation

• M T has gone through ups and downs.

• T oday, Statistic al M a c hine T ranslation leverages the vast

amounts of available translated corpuses.

• While there is room for improvement, machine translation has

made significant progress.
Applications of A I
Machine translation

1 0 0 + languages
Applications of A I
Machine translation
Applications of A I
Robotics: Awesome robots today! NAO, A S I MO, and more!

Credit: B y Momotarou2012, via Wikimedia Commons.

Applications of A I
Recommendation systems (collaborative filtering)
Applications of A I
Search engines
Applications of A I
E m a il
Applications of A I
Face detection

Viola-Jones met hod.

Applications of A I
Face detection

Viola-Jones met hod.

Applications of A I
Face detection

Viola-Jones met hod.

Applications of A I
Face recognition
Applications of A I
Det ect i on of breast cancer in mammography images
Applications of A I
Chess ( 1 9 9 7 ) : Kasparov vs. I B M D e e p Blue

(Left) Copyright 2007, S.M.S.I., Inc. - Owen Williams, The Kasparov Agency, via Wikimedia
Commons (Right) B y James the photographer, via Wikimedia Commons

Powerful search algorithms!

Applications of A I
Autonomous driving

B y User Spaceape on en.wikipedia, via Wikimedia Commons

• D A R P A Grand Challenge
– 2005: 132 miles
– 2007: Urban challenge
– 2009: Google self-driving car
S t a t e - o f - t h e - a r t applications
• Speech recognition • Fraud detection
• A utonomous planning and • Recommendation systems
scheduling • Web search engines
• Financial forecasting • Autonomous cars
• Game playing, video games • Energy optimization
• Spam fighting • Question answering systems
• Logistics planning • Social network analysis
• Robotics (household, surgery, • Medical diagnosis, imaging
navigation) • Route finding
• Machine translation • Traveling salesperson
• Information extraction • Protein design
• V L S I layout • Document summarization
• Automatic assembly • Transportation/scheduling
• Sentiment analysis • Computer animation
S t a t e - o f - t h e - a r t applications
• Speech recognition • Fraud detection
• A utonomous planning and • Recommendation systems
scheduling • Web search engines
• Financial forecasting • Autonomous cars
• Game playing, video games • Energy optimization
• Spam fighting • Question answering systems
• Logistics planning • Social network analysis
• Robotics (household, surgery, • Medical diagnosis, imaging
navigation) • Route finding
• Machine translation • Traveling salesperson
• Information extraction • Protein design
• V L S I layout • Document summarization
• Automatic assembly • Transportation/scheduling
• Sentiment analysis • Computer animation
M a n y more!
Foundation of A I
Foundation of A I
• Philosophy
– Logic, methods of reasoning.
– Mind as physical system that operates as a set of rules.
– Foundations of learning, language, rationality.

• Ma t hemat i c s
– Logic: Formal representation and proof.
– Computation, algorithms.
– Probability.

• Economics
– Formal theory of rational decisions.
– Combined decision theory and probability theory for decision
making under uncertainty.
– Game theory.
– Markov decision processes.
Foundation of A I
• Neuroscience
– Study of brain functioning.
– How brains and computers are (dis)similar.

• Psychology
– How do we think and act?
– Cognitive psychology perceives the brain as an information
processing machine.
– Led to the development of the field cognitive science: how
could computer models be used to study language, memory,
and thinking from a psychological perspective.

• Comput e r engineering
– Cares about how to build powerful machines to make AI
possible.
– E.g., Self-driving cars are possible today thanks to advances
in computer engineering.
Foundation of A I
• Control theory and cybernetics
– Design simple optimal agents receiving feedback from the
environment.
– M odern control theory design systems that maximize an
objective function over time.

• Linguistics
– How are language and thinking related.
– Modern linguistics + AI = Computational linguistics (Nat-
ural language processing).
Summary
• AI is a hard (computational complexity, language, vision, etc),
and a broad field with high impact on humanity and society.

• What can AI do for us is already amazing!

• AI systems do not have to model human/nature but can act

like or be inspired by human/nature.

• How human think is beyond the scope of this course.

• Rational (do the right thing) agents are central to our approach
of AI.

• Note that rationality is not always possible in complicated en-

vironment but we will still aim to build rational agents.
Summary
• A I may be perceived as a scary area! Is A I a threat to our
humankind?

• Professor Stephen Hawking, eminent scientist told B B C :

“ T h e development of full artificial intelligence could spell

the end of the human race.”

• AI is a flourishing and exciting field: everyone can contribute.

• Looking forward for an exciting journey together!