Artificial Intelligence

Areas of AI and Some Dependencies

Knowledge
Search Logic Representation

Machine
Planning
Learning

Expert
NLP Vision Robotics Systems
 What is Artificial
Intelligence ?
 making computers that think
 the automation of activities we associate with
human thinking, like decision making, learning
 the art of creating machines that perform
functions that require intelligence when performed
by people
 the study of mental faculties through the use of
computational models
What is Artificial
Intelligence ?
 the study of computations that make it possible
to perceive, reason and act
 a field of study that seeks to explain and
emulate intelligent behaviour in terms of
computational processes
 a branch of computer science that is concerned
with the automation of intelligent behaviour
 anything in Computing Science that we don't
yet know how to do properly
 Categorization of Intelligent
System

THOUGHT Systems that thinkSystems that think

like humans rationally

Systems that act Systems that act

BEHAVIOUR like humans rationally

HUMAN RATIONAL
 Systems that act like humans:
Turing Test
“The art of creating machines that perform
functions that require intelligence when
performed by people.” (Kurzweil)
“The study of how to make computers do
things at which, at the moment, people are
better.” (Rich and Knight)
 Systems that act like humans

?
You enter a room which has a computer
terminal. You have a fixed period of time to
type what you want into the terminal, and
study the replies. At the other end of the
line is either a human being or a computer
system.
If it is a computer system, and at the end
of the period you cannot reliably determine
whether it is a system or a human, then
the system is deemed to be intelligent.
 Systems that act like humans

The Turing Test approach

a human questioner cannot tell if
 there is a computer or a human answering his
question, via teletype (remote communication)
The computer must behave intelligently
Intelligent behavior
to achieve human-level performance in all
cognitive tasks
 Systems that act like humans
 These cognitive tasks include:
 Natural language processing
 for communication with human
 Knowledge representation
 to store information effectively & efficiently
 Automated reasoning
 to retrieve & answer questions using the stored
information
Machine learning
 to adapt to new circumstances
The total Turing Test
Includes two more issues:
 Computer vision
to perceive objects (seeing)
 Robotics
to move objects (acting)
Systems that think like humans:
cognitive modeling
Humans as observed from ‘inside’
How do we know how humans think?
Introspection vs. psychological experiments
Cognitive Science
“The exciting new effort to make
computers think … machines with minds
in the full and literal sense” (Haugeland)
“[The automation of] activities that we
associate with human thinking, activities
such as decision-making, problem
solving, learning …” (Bellman)
Systems that think ‘rationally’
"laws of thought"
Humans are not always ‘rational’
Rational - defined in terms of logic?
Logic can’t express everything (e.g.
uncertainty)
Logical approach is often not feasible in terms
of computation time (needs ‘guidance’)
“The study of mental facilities through the
use of computational models” (Charniak and
McDermott)
“The study of the computations that make it
possible to perceive, reason, and act”
(Winston)
 Systems that act rationally:
“Rational agent”
Rational behavior: doing the right thing
The right thing: that which is expected to
maximize goal achievement, given the
available information
Giving answers to questions is ‘acting’.
I don't care whether a system:
replicates human thought
processes
makes the same decisions as
humans
uses purely logical reasoning
Systems that act rationally
Logic  only part of a rational agent,
not all of rationality
Sometimes logic cannot reason a correct
conclusion
At that time, some specific (in domain)
human knowledge or information is used
Thus, it covers more generally different
situations of problems
Compensate the incorrectly reasoned
conclusion
Systems that act rationally
Study AI as rational agent –
2 advantages:
It is more general than using logic only
 Because: LOGIC + Domain knowledge
It allows extension of the approach with more
scientific methodologies
Artificial
Produced by human art or effort, rather than
originating naturally.
Intelligence
is the ability to acquire knowledge and
use it" [Pigford and Baur]
So AI was defined as:
AI is the study of ideas that enable
computers to be intelligent.
AI is the part of computer science concerned
with design of computer systems that exhibit
human intelligence
From the above two definitions, we can see
that AI has two major roles:
Study the intelligent part concerned with
humans.
Represent those actions using computers.
Goals of AI
To make computers more useful by letting
them take over dangerous or tedious tasks
from human
Understand principles of human
intelligence
The Foundation of AI
Philosophy
At that time, the study of human intelligence
began with no formal expression
Initiate the idea of mind as a machine and its
internal operations
The Foundation of AI
Mathematics formalizes the three main
area of AI: computation, logic, and
probability
Computation leads to analysis of the
problems that can be computed
 complexity theory
Probability contributes the “degree of belief”
to handle uncertainty in AI
Decision theory combines probability theory
and utility theory (bias)
The Foundation of AI
Psychology
How do humans think and act?
The study of human reasoning and acting
Provides reasoning models for AI
Strengthen the ideas
 humans and other animals can be considered as
information processing machines
The Foundation of AI
Computer Engineering
How to build an efficient computer?
Provides the artifact that makes AI
application possible
The power of computer makes computation
of large and difficult problems more easily
AI has also contributed its own work to
computer science, including: time-sharing,
the linked list data type, OOP, etc.
The Foundation of AI
Control theory and Cybernetics
How can artifacts operate under their own
control?
The artifacts adjust their actions
 To do better for the environment over time
 Based on an objective function and feedback from
the environment
Not limited only to linear systems but also
other problems
 as language, vision, and planning, etc.
The Foundation of AI
Linguistics
For understanding natural languages
 different approaches has been adopted from the
linguistic work
Formal languages
Syntactic and semantic analysis
Knowledge representation
The main topics in AI
Artificial intelligence can be considered under a
number of headings:
Search (includes Game Playing).
Representing Knowledge and Reasoning with it.
Planning.
Learning.
Natural language processing.
Expert Systems.
Interacting with the Environment
(e.g. Vision, Speech recognition,
Robotics)
 Some Advantages of Artificial
Intelligence

more powerful and more useful computers

new and improved interfaces
solving new problems
better handling of information
relieves information overload
conversion of information into knowledge
The Disadvantages

increased costs
difficulty with software development - slow and
expensive
few experienced programmers
few practical products have reached the
market as yet.
Search
 Search is the fundamental technique of AI.
 Possible answers, decisions or courses of action are
structured into an abstract space, which we then search.
 Search is either "blind" or “uninformed":
blind
 we move through the space without worrying about
what is coming next, but recognising the answer if we
see it
informed
 we guess what is ahead, and use that information to
decide where to look next.
 We may want to search for the first answer that satisfies
our goal, or we may want to keep searching until we find
the best answer.
Knowledge Representation &
Reasoning
 The second most important concept in AI
 If we are going to act rationally in our environment, then we
must have some way of describing that environment and
drawing inferences from that representation.
 how do we describe what we know about the world ?
 how do we describe it concisely ?
 how do we describe it so that we can get hold of the right
piece of knowledge when we need it ?
 how do we generate new pieces of knowledge ?
 how do we deal with uncertain knowledge ?
 Knowledge

Declarative Procedural

• Declarative knowledge deals with factoid questions

(what is the capital of India? Etc.)
• Procedural knowledge deals with “How”
• Procedural knowledge can be embedded in
declarative knowledge
Planning
Given a set of goals, construct a sequence of actions
that achieves those goals:
 often very large search space
 but most parts of the world are independent of most
other parts
 often start with goals and connect them to actions
 no necessary connection between order of planning
and order of execution
 what happens if the world changes as we execute the
plan and/or our actions don’t produce the expected
results?
 Learning
If a system is going to act truly appropriately,
then it must be able to change its actions in
the light of experience:
how do we generate new facts
from old ?
how do we generate new
concepts ?
how do we learn to distinguish
different situations in new
environments ?
Interacting with the
Environment
In order to enable intelligent behaviour, we
will have to interact with our environment.
Properly intelligent systems may be
expected to:
accept sensory input
vision, sound, …
interact with humans
understand language, recognise
speech,
generate text, speech and graphics,
…
modify the environment
robotics
History of AI
 AI has a long history
 Ancient Greece
 Aristotle
 Historical Figures Contributed
 Ramon Lull
 Al Khowarazmi
 Leonardo da Vinci
 David Hume
 George Boole
 Charles Babbage
 John von Neuman
 As old as electronic computers themselves (c1940)
History of AI
Origins
The Dartmouth conference: 1956
 John McCarthy (Stanford)
 Marvin Minsky (MIT)
 Herbert Simon (CMU)
 Allen Newell (CMU)
 Arthur Samuel (IBM)
The Turing Test (1950)
“Machines who Think”
By Pamela McCorckindale
 Periods in AI
Early period - 1950’s & 60’s
Game playing
 brute force (calculate your way out)
Theorem proving
 symbol manipulation
Biological models
 neural nets
Symbolic application period - 70’s
Early expert systems, use of knowledge
Commercial period - 80’s
boom in knowledge/ rule bases
 Periods in AI cont’d
? period - 90’s and New Millenium
Real-world applications, modelling, better
evidence, use of theory, ......?
Topics: data mining, formal models, GA’s,
fuzzy logic, agents, neural nets,
autonomous systems
Applications
visual recognition of traffic
medical diagnosis
directory enquiries
power plant control
automatic cars
 Fashions in AI
Progress goes in stages, following funding booms and crises: Some
examples:
1. Machine translation of languages
1950’s to 1966 - Syntactic translators
1966 - all US funding cancelled
1980 - commercial translators available

2. Neural Networks
1943 - first AI work by McCulloch & Pitts
1950’s & 60’s - Minsky’s book on “Perceptrons” stops nearly all work on
nets
1986 - rediscovery of solutions leads to massive growth in neural nets
research

The UK had its own funding freeze in 1973 when the Lighthill report reduced
AI work severely -Lesson: Don’t claim too much for your discipline!!!!
Look for similar stop/go effects in fields like genetic algorithms and
evolutionary computing. This is a very active modern area dating back to
the work of Friedberg in 1958.
AI Applications
Autonomous
Planning &
Scheduling:
Autonomous
rovers.
AI Applications
Autonomous Planning & Scheduling:
Telescope scheduling
AI Applications
Autonomous Planning & Scheduling:
Analysis of data:
AI Applications
Medicine:
Image guided surgery
AI Applications
Medicine:
Image analysis and enhancement
AI Applications
Transportation:
Autonomous
vehicle control:
AI Applications
Transportation:
Pedestrian detection:
AI Applications
Games:
AI Applications
Games:
AI Applications
Robotic toys:
AI Applications
Other application areas:
 Bioinformatics:
 Gene expression data analysis
 Prediction of protein structure
 Text classification, document sorting:
 Web pages, e-mails
 Articles in the news
 Video, image classification
 Music composition, picture drawing
 Natural Language Processing .
 Perception.