ARTIFICIAL INTELLIGENCE

1
ARTIFICIAL INTELLIGENCE IS 524 CHANDRA S.
AMARAVADI
2
ARTIFICIAL INTELLIGENCE
IN THIS PRESENTATION

• Introduction to AI
• Milestones early work
• Machine Intelligence
• The Nature of knowledge
• Knowledge representation
• Examples
• Neural nets
• Expert systems
• Business industry applications

3
INTRODUCTION TO AI
4
THE HISTORY OF AI (FYI)
Major milestones

• Turing m/c test for intelligence --
  1950
• Rockefeller Dartmouth conference --
  1956
• AI as a field of study
• Lisp language --
  1958
• Expert Systems --
  1965
• Dendral Mycin
• Small Talk, Prolog --
  1972
• Fifth Generation Project --
  1981
• Honda robot
  -- 1995
• DARPA driver less vehicle --
  2004
• Stanford driverless car

5
EARLY RESEARCH
Early research on AI focussed on

• Logic
• mathematical reasoning
• Perceptrons
• programs based on on/off model
• Chess
• board game with 8 x 8 squares
• Blocks world
• a world consisting of only blocks

6
SEARCH STRATEGIES
Search strategies are a result of early research
They are algorithms for finding a solution in a
large problem space. Types include

• Breadth-first
• Depth-first
• Heuristic
• Hill-climbing

?
?
?
7
DEFINING INTELLIGENCE
8
DEFINITION

• Artificial Intelligence (AI)

AI is concerned with the principles and
mechanisms for achieving intelligent behavior in
machines
9
THE TEST FOR MACHINE INTELLIGENCE
The Turing test If a person interacting with an
entity from a remote location is unable to judge
whether he/she is dealing with a computer or a
human, and the entity a machine, it is said to
possess intelligence.
Questions
?
Responses
10
ACHIEVING INTELLIGENCE
A common approach to achieving intelligence is to
give machines knowledge and reasoning
Knowledge Reasoning Intelligence
Any other method of achieving intelligence?
11
THE NATURE OF KNOWLEDGE
12
KNOWLEDGE
Knowledge is information organized for problem
solving and can consist of facts, goals, problems
procedures

• The definition of a goal in football
• How to install a water pump
• Painters styles from the modern era
• The process of becoming a GSA contractor
• How to get to a parking lot from a building
• The meaning of Lousiana report in the context
• of a business meeting.

13
THE NATURE OF KNOWLEDGE
There are two types of knowledge from a knowledge
engineering perspective
Declarative Knowledge about an object (size,
shape etc.) Procedural Knowledge about how to
do something. (how to
install memory)
14
KNOWLEDGE REPRESENTATION
15
KNOWLEDGE REPRESENTATION
Knowledge representation is concerned with how to
encode knowledge

• Logic (Predicate logic)
• Frames
• Scripts
• Semantic nets (Snets)
• Rules

16
IDENTIFY THESE AS EXAMPLES OF LOGIC, FRAMES,
SCRIPTS
EXAMPLE 1
EXAMPLE 3
sister_of(X,Y), bird_of_prey(X), father_of(robin,
Y) father_of(robin,_)
If of users gt 300 then, license fee
500 If of users lt 300 then, license fee
300
EXAMPLE 2
is_a dbms software cost
3,000 License cost
check_with_vendor no of users 2000
Max of tables 10,000 Supports ODBC Yes
17
EXAMPLES OF KNOWLEDGE REPRESENTATIONS..
EXAMPLE 5
EXAMPLE 4
bird
bird-of-prey
P PTRANS P to P.O. P ATTEND eyes to counter P
MBUILD line position P PTRANS P to line P PTRANS
M to X X PTRANS Stamps to P
Is-a
Is-a
eagle
has-a
wings
1.5 m
max wingspan
18
NOTES ON FRAMES
Frames are a representation scheme based on the
way we process situations

• slots and fillers
• fillers can have
• values
• is-a links
• procedures (procedural attachments)
• Most useful in classification problems

19
NOTES ON PREDICATE LOGIC
Predicate logic is a representation scheme based
on logic.

• predicates express relationships between
  symbols
• symbols assigned meaning
• father(X, Y) -- father of X is Y
• subsidiary(A, B) subsidiary of A is B
• assertions or propositions are made with
  predicates
• sister(A, B) - parents(A, P, Q), parents(B, P,
  Q)sister of A is B if both have the same
  parents.
• versatile technique useful in general reasoning

20
NOTES ON RULES
Rules are a representation scheme based on the
way we interact with everyday situations (S-R)

• Thought to be used by experts
• Have this format
• IF conditionTHEN action/conclusion
• condition is expressed in terms of variables
• If tax_bracket is high
• if interest_rate gt 5
• Useful if knowledge is conditional
• Most useful in specialized domains
• shallow reasoning

Note S-R stimulus/response
21
NOTES ON SCRIPTS
Scripts are a representation scheme based on the
way we react to complex situations (similar to
frames)

• Description (conceptual representation) of
• actions in a pre-defined situation
• Originated from film industry
• Includes events, actions, actors/props
• Used in understanding stories/narratives

22
NOTES ON SEMANTIC NETS
Semantic nets are a representation scheme based
on associative memory

• node link formalism
• nodes represent concepts or values (atomic)
• links are of two types
• structural represent structure
• descriptive describe object
• Useful for modeling relationships

23
DISCUSSION
1. Represent the following as semantic nets
a) Onyx, Topaz and diamonds are precious stones
b) Diamond is a metamorphic rock! c)
Topaz is blue or yellow in color d) Ann sent
the memo to Mary and Jack. e) John gave the
red rose to his favorite cousin 2. Represent the
following as rules a) For customers paying
with credit card, discount is 15 b) If a
loan is greater than 10,000 classify as risky
c) Poly analyst (a sw program) will not work
unless you enter a registration
code 3. Develop a frame suitable for mortgages
(house, car) 4. Write using predicate logic
a) manager of A is B b) two people are
office mates if they sit next to each other
24
DISCUSSION
What representation (if) any is suitable for each
of the following

• According to the AACSB guidelines, MBA students
• should be capable of providing leadership
  in complex organizational situations.
• A conference paper is accepted if it is written
  with
• clarity, the objectives are well stated,
  methodology is
• sound, and the objectives are fulfilled.
• Insurance coverage is the obligation to
  compensate an insured for loss suffered in a
  mishap or catastrophe

25
EXAMPLE OF PREDICATE LOGIC
facts has_qualification(brad,3.2,620). has_qualif
ication(jill,4.0,540). has_qualification(ted,3.5,3
20). has_qualification(matt,3.8,
600). clauses select(X) - has_qualification(X,G
PA,GMAT), GPAgt3.2, GMATgt550
goals select(brad)? jill? ted? matt?
26
APPLICATION OF FRAMES
Is_a Name Hardness Marks y/n Texture
Structure
Rocks
Sedimentary
Metamorphic
Igneous
Is_a sedimentary rock Name limestone Hardness
soft Marks y/n yes Texture coarse Structure
amorphous
Feldspar
Obsidian
Quartz
27
BRANCHES OF AI
Artificial intelligence
Vision Systems
Expert Systems
NLP
Machine Learning
Robotics
These are traditional branches of AI
28
TRADITIONAL BRANCHES OF AI ..
NLP Natural language processing, concerned with
understanding text and speech as well as with
language translation, handwriting recognition
etc. Expert Systems A computer system that
emulates the decision-making ability of a human
expert. Typical tasks include portfolio
allocation, locomotive repair etc. Vision
Systems Computer based systems where software
performs tasks assimilable to "seeing", usually
aimed at industrial quality assurance, part
selection, defect detection etc. Robotics The
branch of  AI that deals with mechanical or
virtual intelligent agents that can perform tasks
automatically or with guidance, typically by
remote control e.g. painting, welding
etc. Machines Learning Machine learning is the
science of getting computers to act without being
explicitly programmed.
29
OTHER BRANCHES OF AI (FYI)
AI OTHER BRANCHES
Neural Nets
Fuzzy Logic
Genetic Algorithms
Intelligent agents
These are recent extensions of AI
30
EXPERT SYSTEMS
31
EXPERT SYSTEMS
Expert systems incorporate knowledge of domain
experts (SME) predominantly in the form of thumb
rules so as to function like an expert in a
specialized area.
User interface
Inference engine
Knowledge base
KA Subsystem
Note SME Subject Matter Expert KA Knowledge
acquisition
32
EXAMPLE KNOWLEDGE BASE (FYI)
(defrule compare-objectgt(printout t "What do
you want to compare (cartridge-case or
bullet)?")(assert (object-to-compare
(read))))(defrule comparable-ejector-mark(objec
t-to-compare cartridge-case)gt(printout t "Are
the ejector marks comparable (yes or
no)?")(assert (ejector-mark-comparable
(read))))(defrule similar-ejector-mark(and
(object-to-compare cartridge-case)(ejector-mark-c
omparable yes))gt(printout t "What is the
similarity ratio of the ejector marks (high or
low)?")(assert (ejector-mark-similarity (read))))
33
NEURAL NETWORKS
34
NEURAL NETS
Mathematical models to simulate neural models of
the brain, often used in applications requiring
pattern recognition e.g. crime, fraud, intrusion
detection etc.
Neurons
eyes
nose
Dendrites
hair color
gait
Neural Net (a math model)
The brain
35
MORE ON NEURAL NETS (FYI)
X
1
OUTPUT
AF
1
Y
-2
1
Activation Function X Y 2 gt 0
1) X 1, Y 1 gt ? 2) X 2, Y 1 gt ?
36
A NEURAL-NETWORK MODEL
Age
Loyal
Region
Hopper
Call Rate
Lost
Length Cust
Service
37
AI APPLICATIONS
38
BUSINESS APPLICATIONS OF AI
Following is a sampling of AI applications in
businesses

• Marketing
• data/text mining
• Automated voice response
• Production applications
• machine design
• robotics
• paper thickness
• Scheduling of cranes
• Accounting applications
• detect irregularities
• Financial applications
• portfolio selection, credit approval

39
INDUSTRIAL APPLICATIONS OF AI

• driverless vehicles
• facial recognition
• crime prevention
• pothole recognition
• locomotive fault diagnosis
• drones

40
IS THE SINGULARITY NEAR?
Discuss the TECHNICAL feasibility and time frame
for each of the following technologies

• Domestic robots .
• Neural uploads/downloads of information.
• Replacing an organ involved in cognitive
  processing (eyes etc.)
• Flexible manufacturing (fully automated)

What are the impacts of AI on business? Society?
41
The End!