Artificial Intelligence
Goals of this Course: •
This class is a broad introduction to artificial intelligence (AI)
–
–
AI is a very broad field with many subareas
•
We will cover many of the primary concepts/ideas
•
But in 10 weeks we can’t cover everything
•
Other classes in AI you may want to consider:
–
Belief Networks, 276
–
Winter: Probabilistic Learning, 274A
–
Spring: Machine Learning, 273A
If you have taken another class (e.g., undergrad) in AI, you may want to
consider waiving this class and taking a more specialized AI class (feel
free to ask me about this).
Artificial Intelligence
Page 1
History of AI: •
1943: early beginnings
–
•
1950: Turing
–
•
•
Turing's "Computing Machinery and Intelligence“
1956: birth of AI
–
•
McCulloch & Pitts: Boolean circuit model of brain
Dartmouth meeting: "Artificial Intelligence“ name adopted
1950s: initial promise
–
Early AI programs, including
–
Samuel's checkers program
–
Newell & Simon's Logic Theorist
–
1955-65: “great enthusiasm”
–
Newell and Simon: GPS, general problem solver
–
Gelertner: Geometry Theorem Prover
–
McCarthy: invention of LISP
1966—73: Reality dawns
–
Realization that many AI problems are intractable
–
Limitations of existing neural network methods identified
•
Neural network research almost disappears
•
1969—85: Adding domain knowledge
–
–
Development of knowledge-based systems
Success of rule-based expert systems,
•
E.g., DENDRAL, MYCIN
•
But were brittle and did not scale well in practice
•
1986-- Rise of machine learning
Artificial Intelligence
Page 2
–
Neural networks return to popularity
–
Major advances in machine learning algorithms and applications
–
1990-- Role of uncertainty
–
Bayesian networks as a knowledge representation framework
–
1995-- AI as Science
–
Integration of learning, reasoning, knowledge representation
–
AI methods used in vision, language, data mining, etc
What is Intelligence???
 Intelligence:
–
“the capacity to learn and solve problems” (Websters dictionary)
–
in particular,
•
the ability to solve novel problems
•
the ability to act rationally
•
the ability to act like humans
What is Artificial Intelligence?
 Artificial Intelligence:
–
build and understand intelligent entities or agents
–
2 main approaches: “engineering” versus “cognitive modeling”
 Intelligence is the ability to learn about, to learn from, to understand about, and
interact with one’s environment.
 Intelligence is the faculty of understanding
 Intelligence is not to make no mistakes but quickly to understand how to make
them good
 Artificial Intelligence (AI) is usually defined as the science of making computers
do things that require intelligence when done by humans.
 A.I is the study of ideas that enable computers to be intelligent
Artificial Intelligence
Page 3
How Does AI Works??
Artificial intelligence works with the help of
•
Artificial Neurons (Artificial Neural Network)
And
•
Scientific theorems(If-Then Statements, Logics)
What’s involved in Intelligence?
•
•
•
Ability to interact with the real world
–
to perceive, understand, and act
–
e.g., speech recognition and understanding and synthesis
–
e.g., image understanding
–
e.g., ability to take actions, have an effect
Reasoning and Planning
–
modeling the external world, given input
–
solving new problems, planning, and making decisions
–
ability to deal with unexpected problems, uncertainties
Learning and Adaptation
–
we are continuously learning and adapting
–
our internal models are always being “updated”
Artificial Intelligence
Page 4
•
e.g., a baby learning to categorize and recognize animals
Artificial Intelligence: 
Representation & reasoning with knowledge

Sensing, learning & adaptation Search & optimization.

Theoretical principles & applications.

Embedded vs. foreground; real-time vs. offline;

Autonomous vs. supportive, interactive.
Academic Disciplines relevant to AI: •
Philosophy
Logic, methods of reasoning, mind as physical
system, foundations of learning, language,
rationality.
•
Mathematics
Formal representation and proof, algorithms,
computation, (un)decidability, (in)tractability
•
Probability/Statistics
modeling uncertainty, learning from data
•
Economics
utility, decision theory, rational economic agents
•
Neuroscience
neurons as information processing units.
•
Psychology/
how do people behave, perceive, process cognitive
Cognitive Science
information, represent knowledge.
•
Computer
engineering
building fast computers
•
Control theory
design systems that maximize an objective
function over time
•
Linguistics
knowledge representation, grammars
Artificial Intelligence
Page 5
What is Neural Networking??
 Artificial neural networks are composed of interconnecting artificial neurons
(programming constructs that mimic the properties of biological neurons).
Intelligent Systems in Your Everyday Life
•
Post Office
–
•
•
automatic address recognition and sorting of mail
Banks
–
automatic check readers, signature verification systems
–
automated loan application classification
Customer Service
–
automatic voice recognition
–
The Web
–
Identifying your age, gender, location, from your Web surfing
–
Automated fraud detection
–
Digital Cameras
Artificial Intelligence
Page 6
–
Automated face detection and focusing
–
Computer Games
–
Intelligent characters/agents
AI at Forefront of “Computational Revolution”
Industrial revolution
Computational revolution
Artificial Intelligence
Page 7
Acceleration of Methods, Applications, Infrastructure: 
Learning and reasoning prowess

Computation

Memory

Sensors, connectivity, and content
Expectations: AI in daily life: 
Communications

Time management

Health & safety

Education

Goals, informational needs

Games, recreation, activities

Products, purchases, marketing

Opportunistic planning

Augmentation of cognition
Expectations: AI in Science: 
Automated discovery

Design of experiments

Triaging of resources

Interpretation of data

Probing complexity
 Biology, chemistry, medicine, climate
Key insights and technological breakthroughs will be enabled through AI methods
Artificial Intelligence
Page 8
Structure of a Biological Neuron: -
Expectation: AI and Infrastructure : 




Transportation
Commerce decision making
Agriculture
Engineering & architecture
Power & conservation
Artificial Intelligence
Page 9
AI and the Consumer: 
Evolving relationship with computation

Sensing, reasoning & learning

Personalized smart applications

Products & services

Challenges and opportunities with data & privacy
Trends in sensing, reasoning & learning: 
Large quantities of data via new sensing and online processes

Advances in tractable machine learning

New applications and services

Privacy challenges & opportunities
Advances in Machine Learning: 
e.g., Structure search over variables

Generate and test feasible model

Build predictive models
Artificial Intelligence
Page 10
Sensing, Learning, and Privacy: 
Learning preferences about privacy

Protected sensing & personalization

Proactive inference & modeling

Enriched parameters & policies for data sharing

Restricted usage

Partial revelation
Examples Of Artificial Intelligence: Expert Systems!!
 An expert system is a computer program that is designed to hold the
accumulated knowledge of one or more domain experts
 It reasons with knowledge of some specialist subject with a view to solving
problems or giving advice
 They are tested by being placed in the same real world problem solving situation.
Applications of Expert Systems : PUFF: Medical system for diagnosis of respiratory conditions
PROSPECTOR: Used by geologists to identify sites for drilling or mining
Artificial Intelligence
Page 11
Applications of Expert Systems : DENDRAL: Used to identify the structure of chemical compounds. First used in 1965.
LITHIAN: Gives advice to archaeologists examining stone tools
AI Applications: Machine Translation: •
•
Language problems in international business
–
e.g., at a meeting of Japanese, Korean, Vietnamese and Swedish
investors, no common language
–
or: you are shipping your software manuals to 127 countries
–
solution; hire translators to translate
–
would be much cheaper if a machine could do this
How hard is automated translation
–
Very difficult! e.g., English to Russian
–
“The spirit is willing but the flesh is weak” (English)
–
“the vodka is good but the meat is rotten” (Russian)
–
Not only must the words be translated, but their meaning also!
–
Is this problem “AI-complete”?
–
Nonetheless....
–
commercial systems can do a lot of the work very well (e.g., restricted
vocabularies in software documentation)
–
Algorithms which combine dictionaries, grammar models, etc.
–
Recent progress using “black-box” machine learning techniques
Artificial Intelligence
Page 12
Machine Learning!
Machine learning is a scientific discipline concerned with the design and development of
algorithms that allow machines to mimic human intelligence.
There are Three ways that A.I learns:  Failure Driven Learning
 Learning by being Told
 Learning by Exploration
 Modeling exactly how humans actually think
 Modeling exactly how humans actually act
 Modeling how ideal agents “should think”
 Modeling how ideal agents “should act”
•
Modern AI focuses on the last definition
–
we will also focus on this “engineering” approach
–
success is judged by how well the agent performs
Artificial Intelligence
Page 13
Acting humanly: Turing test: •
•
•
Turing (1950) "Computing machinery and intelligence“
"Can machines think?"  "Can machines behave intelligently? “
Operational test for intelligent behavior: the Imitation Game
•
Suggests major components required for AI:
- Knowledge representation
- Reasoning,
- Language/image understanding,
- learning
* Question: is it important that an intelligent system act like a human?
Thinking humanly: •

Cognitive Science approach
–
Try to get “inside” our minds
–
E.g., conduct experiments with people to try to “reverse-engineer” how we
reason, learning, remember, predict
–
Problems
–
Humans don’t behave rationally
e.g., insurance
–
The reverse engineering is very hard to do
The brain’s hardware is very different to a computer program
Artificial Intelligence
Page 14
Thinking rationally: •
Represent facts about the world via logic
•
Use logical inference as a basis for reasoning about these facts
•
Can be a very useful approach to AI

–
E.g., theorem-proves
–
Limitations
–
Does not account for an agent’s uncertainty about the world
E.g., difficult to couple to vision or speech systems
–
Has no way to represent goals, costs, etc (important aspects of real-world
environments)
Acting rationally: •
Decision theory/Economics
–
Set of future states of the world
–
Set of possible actions an agent can take
–
Utility = gain to an agent for each action/state pair
–
An agent acts rationally if it selects the action that maximizes its “utility”
•
Or expected utility if there is uncertainty
•
Emphasis is on autonomous agents that behave rationally (make
the best predictions, take the best actions)
–
on average over time
–
within computational limitations (“bounded rationality”)
Artificial Intelligence
Page 15
Resemblance to Human Mind.... :  The special ability of artificial intelligence is to reach a solution based on
facts rather than on a preset series of steps—is what most closely resembles
the thinking function of the human brain
Human Intelligence VS Artificial Intelligence: -
Human Intelligence : 






Intuition, Common sense,
Judgment, Creativity, Beliefs etc
The ability to demonstrate their
intelligence by communicating
effectively
Plausible Reasoning and Critical
thinking
Humans are fallible
They have limited knowledge bases
Information processing of serial
nature proceed very slowly in the
brain as compared to computers
Humans are unable to retain large
amounts of data in memory.
Artificial Intelligence
Artificial Intelligence: 

Ability to simulate human behavior
and cognitive processes
Capture and preserve human
expertise
Fast Response. The ability to
comprehend large amounts of data
quickly.
No “common sense”
Cannot readily deal with “mixed”
knowledge
May have high development costs

Raise legal and ethical concerns




Page 16
Human Intelligence VS Artificial Intelligence: -
We achieve more than we know. We know more than we understand. We
understand more than we can explain (Claude Bernard, 19th C French
scientific philosopher)
Artificial Intelligence VS Conventional Computing: -
Artificial Intelligence : -
Conventional Computing : -

AI software uses the techniques of
search and pattern matching


Programmers design AI software to
give the computer only the problem,
not the steps necessary to solve it

Conventional computer software
follow a logical series of steps to
reach a conclusion
Computer programmers originally
designed software that
accomplished tasks by completing
algorithms
Psychology And Artificial intelligence: The functionalist approach of AI views the mind as a representational system and
psychology as the study of the various computational processes whereby mental
representations are:


Constructed,
organized, and
Artificial Intelligence
Page 17

Interpreted.
(Margaret Boden's essays written between 1982 and 1988)
Artificial intelligence & our society: Why we need AI??
 To supplement natural intelligence
 for e.g. we are building intelligence in an object so that it can do what we want it
to do, as
 for example-- robots, thus reducing human labor and reducing human mistakes
My Perspective: 
For Humans Intelligence is no more than TAKING a right decision at right time
and

For Machines Artificial Intelligence is no more than CHOOSING a right decision
at right time

I think Artificial intelligence is the Second intelligence ever to exist
Artificial Intelligence
Page 18