Artificial Intelligence

Introduction
Prerequisites

• Comfortable programming in language such as C (or C++) or Java

• Some knowledge of algorithmic concepts such as running times of
algorithms; having some rough idea of what NP-hard means
• Some familiarity with probability (we will go over this from the beginning
but we will cover the basics only briefly)
• Not scared of mathematics, some background in discrete mathematics,
able to do simple mathematical proofs
Grading
• Assignments: 10%
• May discuss with another person; writeup and code must be your own
• Cats: 20%
• Final exam: 70%
 What is artificial intelligence?
• Popular conception driven by science fiction
• Robots good at everything except emotions, empathy,
appreciation of art, culture, …
• … until later in the movie.
• Perhaps more representative of human autism than of (current)
real robotics/AI
• “It is my belief that the existence of autism has contributed to
[the theme of the intelligent but soulless automaton] in no
small way.” [Uta Frith, “Autism”]
• Current AI is also bad at lots of simpler stuff!
• There is a lot of AI work on thinking about what other agents
are thinking
 Real AI
• A serious science.
• General-purpose AI like the robots of science
fiction is incredibly hard
• Human brain appears to have lots of special and
general functions, integrated in some amazing
way that we really do not understand at all (yet)
• Special-purpose AI is more doable (nontrivial)
• E.g., chess/poker playing programs, logistics
planning, automated translation, voice
recognition, web search, data mining, medical
diagnosis, keeping a car on the road, … … … …
 if our system can be more
Definitions of AI rational than humans in
some cases, why not?

Systems that Systems that

focus on action avoids
think like think rationally
philosophical issues humans
such as “is the system
conscious” etc.
Systems that Systems that
act like humans act rationally
• We will follow “act rationally” approach
– Distinction may not be that important
• acting rationally/like a human presumably requires (some
sort of) thinking rationally/like a human,
• humans much more rational anyway in complex domains
“Chinese room”
argument [Searle 1980]
image from http://www.unc.edu/~prinz/pictures/c-room.gif

• Person who knows English but not Chinese sits in room

• Receives notes in Chinese
• Has systematic English rule book for how to write new Chinese
characters based on input Chinese characters, returns his notes
• Person=CPU, rule book=AI program, really also need lots of paper
(storage)
• Has no understanding of what they mean
• But from the outside, the room gives perfectly reasonable answers in
Chinese!
• Searle’s argument: the room has no intelligence in it!
 Turing Test
• (Human) judge communicates with a human and a
machine over text-only channel,
• Both human and machine try to act like a human,
• Judge tries to tell which is which.
• Numerous variants
• Loebner prize
• Current programs nowhere close to passing this
image from http://en.wikipedia.org/wiki/Turing_test
• http://www.jabberwacky.com/
• http://turingtrade.org/
 Turing Test on unsuspecting judges
• It is possible to (temporarily) fool humans who do not
realize they may be talking to a bot
• ELIZA program [Weizenbaum 66] rephrases partner’s
statements and questions (~psychotherapist)
 Is Turing Test the right goal?
• “Aeronautical engineering texts do not define the goal of their field as making
‘machines that fly so exactly like pigeons that they can fool even other pigeons.’”
[Russell and Norvig]
 Lessons from AI research
• Clearly-defined tasks that we think require intelligence and education
from humans tend to be doable for AI techniques
• Playing chess, drawing logical inferences from clearly-stated facts,
performing probability calculations in well-defined environments, …
• Although, scalability can be a significant issue

• Complex, messy, ambiguous tasks that come natural to humans (in

some cases other animals) are much harder
• Recognizing your grandmother in a crowd, drawing the right
conclusion from an ungrammatical or ambiguous sentence, driving
around the city, …

• Humans better at coming up with reasonably good solutions in complex

environments

• Humans better at adapting/self-evaluation/creativity (“My usual

strategy for chess is getting me into trouble against this person… Why?
What else can I do?”)
 Early history of AI
• 50s/60s: Early successes! AI can draw logical conclusions,
prove some theorems, create simple plans… Some initial
work on neural networks…
• Led to overhyping: researchers promised funding agencies
spectacular progress, but started running into difficulties:
• Ambiguity: highly funded translation programs (Russian
to English) were good at syntactic manipulation but bad
at disambiguation
• “The spirit is willing but the flesh is weak” becomes
“The vodka is good but the meat is rotten”
• Scalability/complexity: early examples were very small,
programs could not scale to bigger instances
• Limitations of representations used
History of AI…
•70s, 80s: Creation of expert systems (systems
specialized for one particular task based on
experts’ knowledge), wide industry adoption
•Again, overpromising…
•… led to AI winter(s)
•Funding cutbacks, bad reputation
Good Old-Fashioned AI'' (GOFAI) 
• For example, in the 1960s artificial neural networks were widely
believed to solve all AI problems by imitating the learning
mechanisms in the nature (such as the human central nervous
system and the brain, in particular).

• However, certain negative results about the expressibility of certain

neural computation models quickly lead to pessimism and an AI
winter followed

• The 1980s brought So called expert systems, manipulating

knowledge elicited from domain experts, such as medical doctors

• They showed great promise by solving nicely contained, well-

defined ''toy problems'', but turned out to fail every time when they
were deployed in more complex, real-world problems.

• The second (or the third, depending on the counting) AI winter

lasted from the late 1980s until the mid-1990s.
 Modern AI
• More rigorous, scientific, formal/mathematical
• Fewer grandiose promises
• Divided into many subareas interested in particular
aspects
• More directly connected to “neighboring” disciplines
• Theoretical computer science, statistics, economics, operations
research, biology, psychology/neuroscience, …
• Often leads to question “Is this really AI”?
• Some senior AI researchers are calling for re-integration of
all these topics, return to more grandiose goals of AI
• Somewhat risky proposition for graduate students and junior
faculty…
 Modern AI
• Modern AI introduced methods that were able to handle uncertain and
imprecise information, most notably by probabilistic methods, and which had
the great advantage that it was designed to work in the real world.

• The rise of modern AI has continued until present day, further boosted by the
come-back of neural networks under the label Deep Learning

• The significance of AI in the society is going to stay. Today, we live our life
surrounded by AI, most of the time happily unaware of it:
 the music that we listen,
 the products that we buy online,
 the movies and series that we watch,
 our routes of transportation,
 and the information that we have available

• All are influenced more and more by AI.

PHILOSOPHY O
F AI
INTELLIGENT

"strong "weak AI"

AI" rational
agents
"swarm
intelligence"
THINKING BEHAVIOR
cognitive Turing
science test
neuroscience
psychology

HUMAN-LIKE
W H AT I S A I , R E A L
LY ? ''cool things that computer can't do.''
The joke is that under this definition, AI can never
make any progress: as soon as we find a way to do
something cool with a computer, it stops being an
AI problem.

MACHINE VISION
NLP
ROUTE PLANNING SPEECH GAMES

MACHINE LEARNING LOGICAL REASONING

INFORMATION RETRIEVAL DATA MINING

RECOMMENDATION

MACHINE
TRANSLATION
 Some AI videos
• Note: there is a lot of AI that is not quite this “sexy” but still very
valuable!
• E.g. logistics planning – DARPA claims that savings from a single AI planning
application during 1991 Persian Gulf crisis more than paid back for all of
DARPA’s investment in AI, ever. [Russell and Norvig]
• http://www.youtube.com/watch?v=1JJsBFiXGl0&feature=related
• http://www.youtube.com/watch?v=ICgL1OWsn58&feature=related
• http://www.cs.utexas.edu/~kdresner/aim/video/fcfs-insanity.mov
• http://www.youtube.com/watch?v=HacG_FWWPOw&feature=related
• http://videolectures.net/aaai07_littman_ai/
• http://www.ai.sri.com/~nysmith/videos/SRI_AR-PA_AAAI08.avi
• http://www.youtube.com/watch?v=ScXX2bndGJc
This course
• Focus on general AI techniques that have been useful in many
applications
• Will try to avoid application-specific techniques (still
interesting and worthwhile!)
Topics
• Search
• Constraint satisfaction problems
• Game playing
• Logic, knowledge representation
• Planning
• Probability, decision theory, game theory, reasoning
under uncertainty
• Machine learning, reinforcement learning
 Nonexhaustive list of AI publications
• General AI conferences: IJCAI, AAAI, ECAI
• Reasoning under uncertainty: UAI
• Machine learning: ICML, NIPS
• Multiagent systems: AAMAS
• Vision: ICCV, CVPR

• Some journals: Artificial Intelligence, Journal of

AI Research, Machine Learning, Journal of ML
Research, Journal of Autonomous Agents and
Multi Agent Systems
• AI Magazine