1. Artificial
Intelligence

2. 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.
 Make sense out of ambiguous or contradictory messages.
 Respond quickly and successfully to new situations.
 Use reasoning to solve problems.
Intelligence is not to make no mistakes but quickly to understand how to
make them good
(German Poet)

3. 


A branch of computer science whose goal is the design of
machines that have attributes associated with human
intelligence, such as learning, reasoning, vision,
understanding speech, and, ultimately, consciousness.
Computer software that can mimic the learning capability
of a human. The use of programs to enable machines to
perform tasks which humans perform using their
intelligence.
The term was coined in 1956 by John McCarthy
at the Massachusetts Institute of Technology.

4. 
Examples:
 Defeating the best
human chess players.
 Driving hundreds of
miles through the
desert unaided.
 Chatting in internet
chat-rooms.
 Examining x-rays for
tumors.

5. Currently, no computers exhibit full artificial intelligence (that is, are
able to simulate human behaviour). The greatest advances have
occurred in the field of games playing. The best computer chess
programs are now capable of beating humans. In May, 1997, an IBM
super-computer called Deep Blue defeated world chess champion
Gary Kasparov in a chess match.
In the area of robotics, computers are now widely used in assembly
plants, but they are capable only of very limited tasks. Robots have
great difficulty identifying objects based on appearance or feel, and
they still move and handle objects clumsily.
Natural-language processing offers the greatest potential rewards
because it would allow people to interact with computers without
needing any specialized knowledge. You could simply walk up to a
computer and talk to it. Unfortunately, programming computers to
understand natural languages has proved to be more difficult than
originally thought.

6. There are also voice recognition systems that can convert spoken sounds
into written words, but they do not understand what they are writing;
they simply take dictation. Even these systems are quite limited -you must speak slowly and distinctly.
In the early 1980s, expert systems were believed to represent the
future of artificial intelligence and of computers in general.
Many expert systems help human experts in such fields as medicine and
engineering, but they are very expensive to produce and are helpful
only in special situations.
Today, the hottest area of artificial intelligence is neural networks,
which are proving successful in a number of disciplines such as voice
recognition and natural-language processing.
There are several programming languages that are known as AI
languages because they are used almost exclusively for AI
applications. The two most common are LISP and Prolog.

7. ▪ Foundation of AI is
based on
▪ Mathematics
▪ Neuroscience
▪ Control Theory
▪ Linguistics

8. 
More formal logical methods
▪ Boolean logic
▪ Fuzzy logic

Uncertainty
▪ The basis for most modern approaches to
handle uncertainty in AI applications can be
handled by
 Probability theory
 Modal and Temporal logics

9. 
How do the brain works?
 Early studies (1824) relied on injured and abnormal
people to understand what parts of brain work
 More recent studies use accurate sensors to correlate
brain activity to human thought
▪ By monitoring individual neurons, monkeys can now control a
computer mouse using thought alone
 Moore‟s law states that computers will have as many
gates as humans have neurons in 2020
 How close are we to have a mechanical brain?
▪ Parallel computation, remapping, interconnections,….

10.  Machines can modify their behavior in response
to the environment (sense/action loop)
▪ Water-flow
regulator,
governor, thermostat
steam
engine
 The theory of stable feedback systems (1894)
▪ Build systems that transition from initial
state to goal state with minimum energy
▪ In 1950, control theory could only describe
linear systems and AI largely rose as a
response to this shortcoming

11. 
Speech demonstrates so much of human
intelligence
 Analysis of human language reveals thought taking
place in ways not understood in other settings
▪ Children can create sentences they have never heard
before
▪ Language and thought are believed to be tightly
intertwined

12. 






More permanent
Ease of duplication and dissemination
Less expensive
Consistent and thorough
Can be documented
Can execute certain tasks much faster than a
human can
Can perform certain tasks better than many or
even most people

13. 


Natural intelligence is creative
People use sensory experience directly
Can use a wide context of experience in
different situations
AI - Very Narrow Focus

14. Artificial
intelligence
Vision
systems
Learning
systems
Robotics
Expert systems
Neural networks
Natural language
processing

15. Artificial intelligence includes :





Games playing: programming computers to play games such as
chess and checkers.
Expert systems : programming computers to make decisions in real-life
situations. (for example, some expert systems help doctors diagnose
diseases based on symptoms)
Natural language : programming computers to understand natural
human languages.
Neural networks : Systems that simulate intelligence by attempting
to reproduce the types of physical connections that occur in animal
brains.
Robotics : programming computers to see and hear and react to
other sensory stimuli.

16. 
Alan Turing (1912 - 1954)
 Proposed a test - Turing’s
Interrogator
Imitation Game
▪ Tests the intelligence of the
computer.
 Phase 1:
▪ Man and woman separated
from an interrogator.
▪ The interrogator types in a
question to either party.
▪ By observing responses, the
interrogator‟s goal was to
identify which was the man
and which was the woman.
Honest Woman
Lying Man

17. 
Phase 2 of the Turing‟s test:
Interrogator
 The man was replaced
by the computer.
 If the computer could
fool the interrogator as
often as the person
did, it could be said
that the computer had
displayed intelligence.
Honest Woman
Computer

18. 



According to Darlington:
“An expert system is a program that attempts to mimic human
expertise by applying inference methods to a specific body
of knowledge.”
The term expert system is used in a seminal paper by Alan
Turing in 1937 related to a study in AI.
An Expert System (ES) is a computer program that reasons
using knowledge to solve complex problems.
Traditionally, computers solve complex problems by
arithmetic calculations; and the knowledge to solve the
problem is only known by the human programmer.

19. ES's are:
1. Open to inspection, both in presenting intermediate steps
and in answering questions about the solution process.
2. Easily modified, both in adding and deleting skills from
the knowledge base.
3. Heuristic, in using knowledge to obtain solutions
Development of Expert Systems will allow us not only to
provide very powerful technical capabilities but also to
further nurture our own understanding of human thought
process.

20. 
An ES will normally have two aspects:
 A development environment
 A consultation environment


The former is used by the system builder to
modify the system. The later is used by the
non-expert to obtain knowledge or advice.
It is the latter which is thought of as an ES.

21. 
An ES is a program with various components:
1.
2.
3.
4.
5.
6.
7.
Knowledge acquisition subsystem
Knowledge base
Inference engine
User interface
Explanation subsystem
Blackboard
Knowledge refinement subsystem

22. Explanation
facility
Knowledge
base
Inference
engine
Knowledge
base
acquisition
facility
Experts
User
interface
User

23. An ES may obtain input from an online data source
(database, text file, web page, etc).
 An ES may be used to monitor a physical system, in
which case input may come directly from sensing
devices.
 An ES may be used to control a physical system, in
which case output will be signals to the system.
 When interacting with humans, standard HCI
(Human-Computer Interaction) concerns apply.


24. 



The power of problem solving is primarily the consequence of the
knowledge base and secondarily on the inference method employed.
A storehouse of knowledge primitives. The design of knowledge
representation scheme impacts the design of the inference engine, the
knowledge updating process, the explanation process and the overall
efficiency of the system.
Therefore the selection of the knowledge representation scheme is one of
the most critical decision in ES design.
Knowledge update is done either :
1. Manual
 by the knowledge engineer
 domain expert
2. Machine learning

25. 




The inference engine controls the reasoning involved when
the system is run.
It has its own mechanism for interpreting the stored
knowledge (in the appropriate form), and for sequencing the
steps involved in reaching conclusions.
Inference here means any of the methods by which the system
reaches conclusions.
Facts: All animals breathe oxygen.
All dogs are animals.
Infer: All dogs breathe oxygen.

26. If the user is to have confidence in the output from an
ES, it will be important for the ES to have ways of
explaining how its conclusions were arrived at.
It will be useful to allow the user to ask.
 In response to a question from the ES:

WHY (did you ask that question)?

After a conclusion has been presented:
HOW (did you reach that conclusion)?

27. This just means a place where temporary working may be
stored, where it is accessible to various component parts of a large
ES.
This may include, for example, a (dynamic) „agenda‟ --- a list of
tasks to be done (by the ES).
It may also include a list of intermediate conclusions, or results of
searches, in order to avoid duplication of effort.
Not all ES will use (or need) a blackboard.

28. Knowledge refinement means analyzing experience and
adjusting the body of stored knowledge as a result.
People do this all the time, and a good ES can do it too.
This may consist merely of saving previous results for future
reference, to avoid repeating searches or computations.
OR it may involve feedback from the user, e.g.
You (the ES) gave me this advice and it was BAD/GOOD

29. Strategic goal setting
Planning
Design
Decision making
Quality control and monitoring
Diagnosis
Explore impact of strategic goals
Impact of plans on resources
Integrate general design principles and
manufacturing limitations
Provide advise on decisions
Monitor quality and assist in finding solutions
Look for causes and suggest solutions

30. 








Scarce expertise made available.
Integration of expertise from different sources.
Improved quality (e.g. where an ES assists in design).
Ability to work with incomplete information.
Reduced system downtime (ES monitors or finds
faults).
Training (users gain expertise from the ES).
Makes expertise available in remote locations.
ES can work faster than people.
Reliability (ES will not get tired or bored).

31. 



Expert systems are difficult and expensive to develop and
maintain.
Like all software, ES may contain errors. But unlike other
software systems, ES may be designed to cope with
incomplete or inconsistent information.
If an ES gives a wrong conclusion, it may be difficult to know
whether this was caused by an error in the system or by an
error in the information given to it.
ES are designed to be used by non-experts. As above, they are
designed not to fail, so errors may show only in wrong
conclusions, and a user without expertise may not be in a
position to recognize a wrong conclusion.

32. PUFF:
Medical system
for diagnosis of respiratory conditions
PROSPECTOR:
Used by geologists to identify sites for drilling
or mining

33. If an intelligent agent is supposed to behave like a human
being, it may need to learn. Learning is a complex biological
phenomenon that is not even totally understood in humans.
Enabling an artificial intelligence agent to learn is definitely not
an easy task. However, several methods have been used in the
past that create hope for the future. Most of the methods use
inductive learning or learning by example. This means that a
large set of problems and their solutions is given to the machine
from which to learn.

34. • Animals are able to react adaptively to changes in their external and internal
environment, and they use their nervous system to perform these behaviours.
• An appropriate model/simulation of the nervous system should be able to produce similar
responses and behaviours in artificial systems.
• The nervous system is build by relatively simple units, the neurons, so copying their
behaviour and functionality should be the solution.
• The spikes travelling along the axon of the pre-synaptic neuron trigger the release of
neurotransmitter substances at the synapse.
• The neurotransmitters cause excitation or inhibition in the dendrite of the post-synaptic
neuron.
• The integration of the excitatory and inhibitory signals may produce spikes in the postsynaptic neuron.
• The contribution of the signals depends on the strength of the synaptic connection.

35. Dendrites: Accepts Inputs
Soma: Processes the Inputs
Axon: Turns the processed inputs into outputs
Synapses: The electrochemical contact between neurons

36. Axons
Synapses Dendrites
X1
W1
X2
W3
Axon
W2
X3
Body
(Soma)
f
Output (y)
W0
Xn
Wn
Bias

37. Inputs
Output
An artificial neural network is composed of many artificial neurons that are
linked together according to a specific network architecture. The objective of
the neural network is to transform the inputs into meaningful outputs.

38. A collection of neurons which are interconnected. The output
of one connects to several others with different strength
connections. This collection of neurons is termed as multilayer networks. Initially, neural networks have no knowledge.
(All information is learned from experience using the
network.)
Neuron 1
Input 1
Output from
Neuron 1
Input 2
Input 3
Neuron 2
Output from
Neuron 2

39. Each processing element in an artificial neural net is analogous to
a biological neuron
 An element accepts a certain number of input values (dendrites)
and produces a single output value (axon) of either 0 or 1.
 Associated with each input value is a numeric weight (synapse)
The effective weight of the element is the sum of the weights
multiplied by their respective input values.
v1 * w1 + v2 * w2 + v3 * w3
 Each element has a numeric threshold value.
 If the effective weight exceeds the threshold, the unit produces an
output value of 1.
 If it does not exceed the threshold, it produces an output value of
0.

40. 
Artificial models of the brain are of two
distinct types:
 Electronic: Has electronic circuits that act
like neurons.
 Software: This version runs a program on
the computer that simulates the action of the
neurons.

41. Tasks to be solved by artificial neural networks:
• controlling the movements of a robot based on selfperception and other information (e.g., visual information);
• deciding the category of potential food items (e.g., edible
or non-edible) in an artificial world;
• recognizing a visual object (e.g., a familiar face);
• predicting where a moving object goes, when a robot
wants to catch it.

42. Three basic types of processing occur during human/
computer voice interaction:
Voice synthesis
Using a computer to recreate the sound of human speech
Voice recognition
Using a computer to recognize the words spoken by a
human
Natural language comprehension
Using a computer to apply a meaningful interpretation
to human communication
42

43. Dynamic voice generation
A computer examines the letters that make up a word and
produces the sequence of sounds that correspond to those
letters in an attempt to vocalize the word.
Phonemes
The sound units into which human speech has been
categorized.
Recorded speech
A large collection of words is recorded digitally and
individual words are selected to make up a message
Many words must be recorded more than once to reflect
different pronunciations and inflections.
43

44. Problems with understanding speech
 Each person's sounds are unique.
 Each person's shape of mouth, tongue, throat, and nasal




cavities that affect the pitch and resonance of our spoken
voice are unique.
Speech impediments, mumbling, volume, regional
accents, and the health of the speaker are further
complications.
Humans speak in a continuous, flowing manner, stringing
words together.
Sound-alike phrases like “ice cream” and “I scream”.
Homonyms such as “I” & “eye” or “see” & “sea”.
44

45. Humans clarify these situations by context, but that requires
another level of comprehension. Voice-recognition systems still
have trouble with continuous speech.
Voiceprint
The plot of frequency changes over time representing the sound
of human speech
A human trains a voice-recognition system by speaking a word
several times so the computer gets an average voiceprint for a
word
Used to authenticate the declared
sender of a voice message
45

46. Natural language is ambiguous!
Lexical ambiguity
The ambiguity created when words have multiple meanings.
Syntactic ambiguity
The ambiguity created when sentences can be constructed in
various ways.
Referential ambiguity
The ambiguity created when pronouns could be applied to
multiple objects.
46

47. Lexical ambiguity
Stand up for your country.
Take the street on the left.
Can you think
of
some others?
Syntactic ambiguity
I saw the bird watching from the corner.
I ate the sandwich sitting on the table.
Referential ambiguity
The bicycle hit the curb, but it was not damaged.
John was mad at Bill, but he didn't care.
47

48. Neural networks can be used when enough preestablished inputs and outputs exist to train the
network. Two areas in which neural networks have
proved to be useful are optical character recognition
(OCR), in which the intelligent agent is supposed to
read any handwriting, and credit assignment, where
different factors can be weighted to establish a credit
rating, for example for a loan applicant.

50. Pros
HUMAN INTELLIGENCE



Intuition, Common
sense, Judgments, Creativit
y, Beliefs etc
The ability to demonstrate
their intelligence by
communicating effectively
Plausible Reasoning and
Critical thinking
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.

51. Cons
HUMAN INTELLIGENCE
ARTIFICIAL INTELLIGENCE
• 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.


No “common sense”
Cannot readily deal with
“mixed” knowledge
May have high
development costs
Raise legal and ethical
concerns