A Descriptive Presentation

on
Artificial Intelligence

By
A SAI MADHURI
TOPICS TO BE REVEALED

 INTRODUCTION

 ARTIFICIAL INTELLIGENCE

 HOW IT WORKS

 HUMAN Vs ARTIFICIAL INTELLIGENCE

 SEARCH TECHNIQUES OF AI

 APPLICATIONS…

 CONCLUSION..
The Origins of AI Hype

1950 Turing predicted that in about fifty years "an

average interrogator will not have more than a 70
percent chance of making the right identification
after five minutes of questioning".

1957 Newell and Simon predicted that "Within ten

years a computer will be the world's chess champion,
unless the rules bar it from competition."
What exactly
is
Artificial Intelligence???
“Artificial intelligence (AI) is a branch of computer
science that deals with intelligent behavior,
learning, and adaptation in machines”
(Wikipedia)

 Defined - As the ability of a machine to think for itself…

 As a Branch of science ...
 Making hands free………….
 According to Webster’s Dictionary it is the characteristics of
a machine programmed to imitate human intelligence
functions.
 Making a step wise stud
A step wise representation of AI

Preparing
Burrowing
model of AI Characteristics
from HI

Influence on behavior Appling them as

approach algorithm

Generating
Requirements
How does AI works

Artificial intelligence = machine intelligence + human intelligence

Machine intelligence :- varies according to the profit or gain we

obtain from them & also depends on the current technologies.
example:-- robotic eyes needs some technology that can work
like human eyes . .
Human Intelligence:--
 Understand & apply knowledge
 Ability to acquire
 Knowledge of both conscious &unconscious
 Thought, imagination
 Write , Memorize
 Recall facts ,express &feel emotions
 HUMAN
VS
ARTIFICIAL INTELLIGENCE
 It is hard to distinguish between that who is better in
chess
Human or Artificial Intelligence. ????

Deep Blue because of its capability to calculate up to

4,000,000 chess moves per second ..
Human chess player who could only calculate up to three
moves in a second.

 Deep Blue makes its move by using its evaluation

function. The evaluation function is an algorithm that
measures the chess position.

Positions with +ve values :-good for ‘White’ and

-ve values :- Good for ‘Black’
Artificial Intelligence (AI) is a subfield of computer science closely
tied with biology and cognitive science.
 AI is concerned with computing techniques and models
that simulate/investigate intelligent behavior.
 AI research builds upon our understanding of the brain
and evolutionary development.
 in return, AI research provides insights into the way the
brain works, as well as the larger process of biological
evolution.
Two hot research areas in AI are:
1. neural networks: building a model of the brain and
"training" that model to recognize certain types of
patterns.
2. genetic algorithms: "evolving" solutions to complex
problems (especially problems that are intractable using
other methods).
Neural networks are based on the brain metaphor
large number of simple, neuron-like processing elements
large number of weighted connections between neurons
note: the weights encode information, not symbols!
parallel, distributed control
emphasis on learning

McCulloch & Pitts (1943) described an artificial neuron

– inputs are either electrical impulse (1) or not (0)
– each input has a weight associated with it
– the activation function multiplies each input value by its weight
– if the sum of the weighted inputs >= ,
then the neuron fires (returns 1), else doesn't fire (returns 0)


if wixi >= , output = 1
w w
if wixi < , output = 0
1 n
w 2

...

x1 x2 xn
Applications of Neural networks

Function approximation, or regression analysis.

Classification, including pattern and sequence recognition.

Data processing, including filtering, clustering, blind source separation

and compression.

Robotics, including directing manipulators, 

Computer numerical control.

Types of Neural networks

 Feed forward neural network

 Radial basis function network

 Recurrent network

 Stochastic network

 Modular neural network

 Physical neural network

Genetic algorithms
The genetic algorithm (GA) is a search heuristic that
mimics the process of natural evolution. This heuristic
is routinely used to generate useful solutions to 
optimization and search problems.
Steps for algorithm
• A successor state is generated by combining two parent states
• Start with k randomly generated states (population)
• A state is represented as a string over a finite alphabet (often
a string of 0s and 1s)
• Evaluation function (fitness function). Higher values for better
states.
• Produce the next generation of states by selection, crossover,
and mutation
• Fitness function: number of non-attacking pairs of queens (min
= 0, max = 8 × 7/2 = 28)
• 24/(24+23+20+11) = 31%
• 23/(24+23+20+11) = 29% etc

Example

15
Application of genetic algorithm

Artificial creativity
Bio informatics
Computer automated design
Data mining
Software engineering
Neural networks are patterned after the processes underlying
brain activity
 Artificial neurons are interconnected into networks.
 Information is sub-symbolic, stored in the strengths of the
connections.

Genetic algorithms represent an approach to problem-solving

that is patterned after the processes underlying evolution
 potential solutions to problems form a population better
(more fit) .
 solutions evolve through natural selection.
Search techniques of Artificial Intelligence
• Best-first search
• Greedy best-first search
• A* search
• Heuristics
• Local search algorithms
• Hill-climbing search
• Simulated annealing search
• Local beam search
Tree search
A search strategy is defined by picking the order of
node expansion

Best-first search
Idea: use an evaluation function f(n) for each node
estimate of "desirability"
Expand most desirable unexpanded node

Implementation:
Order the nodes in fringe in decreasing
order of desirability

Special cases:
greedy best-first search
A* search
Greedy best-first search
Evaluation function f(n) = h(n) (heuristic)
= estimate of cost from n to goal
e.g., hSLD(n) = straight-line distance from n to Bucharest.
Greedy best-first search expands the node that appears to
be closest to goal.

Properties of greedy best-first search

Complete? No – can get stuck in loops,

e.g., Iasi  Neamt  Iasi  Neamt 
Time? O(bm), but a good heuristic can give dramatic
improvement
Space? O(bm) -- keeps all nodes in memory
Optimal? No
A* search
• Idea: avoid expanding paths that are already expensive
• Evaluation function f(n) = g(n) + h(n)
• g(n) = cost so far to reach n
• h(n) = estimated cost from n to goal
• f(n) = estimated total cost of path through n to goal

Properties of A*

• Complete? Yes (unless there are infinitely many nodes with f ≤

f(G) )
• Time? Exponential
• Space? Keeps all nodes in memory
• Optimal? Yes
Local search algorithms
• In many optimization problems, the path to the goal is
irrelevant; the goal state itself is the solution

• State space = set of "complete" configurations

• Find configuration satisfying constraints, e.g., n-queens

• In such cases, we can use local search algorithms

• keep a single "current" state, try to improve it

Example: n-queens
Hill-climbing search

Problem: depending on initial state, can get stuck

in local maxima. 23
Simulated annealing search
Idea: escape local maxima by allowing some "bad" moves
but gradually decrease their frequency

 Used in VLSI layout, airline scheduling, etc

Local beam search

• Keep track of k states rather than just one.

• Start with k randomly generated states.
• At each iteration, all the successors of all k states are
generated.
• If any one is a goal state, stop; else select the k best
successors from the complete list and repeat.
Application of AI

Computer science
Finance
Medicine
Heavy industry
Transportation
Telecommunication
Toys and Games
Music
Aviation
Biometrics: Unlocking Doors With Your Eyes.

# It is not science fiction to think that our eyes could very

soon be the key to unlocking our homes, accessing our bank
accounts and logging on to our computers, according to
Queensland University of Technology researcher Sammy ,,,

# By using iris recognition it is possible to confirm the identity

of a person based on who the person is rather than what the
person possesses, such as an ID card or password.
Robotic surgery
 
Robotic surgery is the use of robots in performing surgery
Three major advances aided by surgical robots have been remote surgery,
minimally invasive surgery,

Laparoscopic surgery — Laparoscopic surgery, also called keyhole surgery (when

natural body openings are not used), bandaid surgery, or minimally invasive surgery
(MIS) 
Minimally invasive procedure — A minimally invasive medical procedure is defined as
one that is carried out by entering the body through the skin or through a body cavity .
Urology — Urology is the field of medicine that focuses on the urinary tracts of males
and females, and on the reproductive system of males. In men, the
 
 Hysterectomy — A hysterectomy is the surgical removal of the uterus, usually done
by a gynecologist.
Humanoid robot:

A humanoid robot is a robot with its overall appearance based on

that of the human body.
# In general humanoid robots have a torso with a head, two
arms and two legs, although some forms of humanoid robots
may model only part of the body, for example, from the waist
up.
# Some humanoid robots may also have a 'face', with 'eyes'
and 'mouth'.
•Androids are humanoid robots built to resemble a male
human,
•Gynoids are humanoid robots built to resemble a human
female..
Robot calibration:
Robot calibration is the process of identifying the real
geometrical parameters in the kinematic structure of an
industrial robot, i.e., the relative position and orientation of
links and joints in the robot.

# A calibrated robot has a higher absolute positioning accuracy

than an uncalibrated one, i.e., the real position of the robot end
effectors corresponds better to the position calculated from the
mathematical model of the robot.

# Industrial robot — An industrial robot is an automatically

controlled, reprogrammable, multipurpose manipulator
programmable in three or more axes.
 
Robots Taking Over The Job On Offshore Oil
Drilling Platforms:

 In the future, offshore platforms could be run by robots alone,

with human beings staying on land.