Artificial Intelligence

| |

|
@
Majid Fakhi 15
Khaleel ur Rehman 35
Abdul Basith 43
Mohammed Aadil 45
Sheikh Abdul Bur 51
Mohd irfan 34
Artificial intelligence (AI)
ÿ Computers with the ability to duplicate the functions of
the human brain
ÿ The field of computer science that deals with

development of intelligent machines that can learn and
infer from the experiences like a human brain.
ÿ AI textbooks define as "the study and design of

intelligent agentsµ.
hat is artificial intelligence?
å Artificial intelligence (AI) is the intelligence of machines

and the branch of computer science which aims to create it.
å Intelligence exhibited by an artificial (non-natural, man-

made) entity; the study and design of intelligent agents,
where an intelligent agent is a system that perceives its
environment and takes actions which maximize its chances
of success.
÷xample:
|

Major Branches of AI
Perceptive system or Artificially intelligent system
å A system that approximates the way a human sees,
hears, and feels objects
Vision system
å Capture, store, and manipulate visual images and
pictures
Robotics
å Mechanical and computer devices that perform tedious
tasks with high precision
÷xpert system
å Stores knowledge and makes inferences
Major Branches of AI
ÿ Learning system
Computer changes how it functions or reacts to
situations based on feedback
ÿ àatural language processing

Computers understand and react to statements and
commands made in a ´naturalµ language, such as
÷nglish
ÿ àeural network
Computer system that can act like or simulate the
functioning of the human brain
Benefits of Artificial Intelligence
Artificial intelligence has been used in a

wide range of fields including medical
diagnosis, stock trading, robot control,
scientific discovery and toys.
Artificial intelligence is widely used in the

field of gaming e.g. the game of chess.
÷asier copying. Once an artificial mind is

trained in a task, that mind can then be
copied very easily, compared to the training
of multiple people for the same task.
]isadvantages of Artificial Intelligence
If robots start replacing human resources in every field, we will

have to deal with serious issues like unemployment in turn
leading to mental depression, poverty and crime in the society.
Replacing human beings with robots in every field may not be a

right decision to make.
Major disadvantages of intelligent machines is that they cannot

be ¶human·.
Limited sensory input.

hat is àeural àetwork?
å Computer architecture in which processors are connected in

a manner suggestive of connections between neurons;
å Can learn by trial and error any network of neurons or
nuclei that function together to perform some function in the
body
à |à |

|à |à
Layers of àeural àetworks
÷ach Aàà is composed of a collection of perceptions grouped in

layers.
The three layers:

input, intermediate (called the
¦ ) and output.
Several hidden layers can be
placed between the input and
output layers.
Types of Layers
å The input layer

Introduces input values into the network
ào activation function or other processing
å The hidden layer

Perform classification of features
Two hidden layers are sufficient to solve any problem
Features imply more layers may be better
å The output layer

Functionally just like the hidden layers
Outputs are passed on to the world outside the neural network.
Benefits of àeural àetwork
å Pattern recognition, learning, classification,

generalization and abstraction, and interpretation of
incomplete and noisy inputs
å Provide some human problem-solving characteristics
å Robust
å Fast, flexible and easy to maintain
å @
¦

A]VAàTAG÷S«
å A neural network can perform tasks that a linear program

can not.
å hen an element of the neural network fails, it can continue

without any problem by their parallel nature.
å A neural network learns and does not need to be

reprogrammed.
å It can be implemented in any application.
å It can be implemented without any problem.

]ISA]VAàTAG÷S«
This causes the loss of human control over those "deemed
machines".
They may dominate us in the near future.
Sometimes it may cause the destruction of the "entire beautiful

human race"
The architecture of a neural network is different from the

architecture of microprocessors therefore needs to be emulated.
Requires high processing time for large neural networks.

APPLICATIOàS OF AI & àà
å Artificial Intelligence in the form of expert systems and

neural networks have applications in every field of human
endeavor.
å Artificial intelligence has been used in a wide range of

fields including medical diagnosis, stock trading, robot
control, scientific discovery and toys.
å àeural àetworks are used in the recognition systems such

as voice recognition.

Artificial Intelligence

Uploaded by

Copyright:

Available Formats

Artificial Intelligence

Uploaded by

Document Information

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Artificial Intelligence

Uploaded by

Copyright:

Available Formats

What are the main topics discussed in the document?

What are the main topics discussed in the document?

How is the information organized and presented?

How is the information organized and presented?

| |

ÿ The field of computer science that deals with

ÿ AI textbooks define as "the study and design of

å Artificial intelligence (AI) is the intelligence of machines

å Intelligence exhibited by an artificial (non-natural, man-

ÿ àatural language processing

Artificial intelligence has been used in a

Artificial intelligence is widely used in the

÷asier copying. Once an artificial mind is

If robots start replacing human resources in every field, we will

Replacing human beings with robots in every field may not be a

Major disadvantages of intelligent machines is that they cannot

Limited sensory input.

å Computer architecture in which processors are connected in

à |à  | 

÷ach Aàà is composed of a collection of perceptions grouped in

The three layers:

å The input layer

å The hidden layer

å The output layer

å Pattern recognition, learning, classification,

å Provide some human problem-solving characteristics

å Fast, flexible and easy to maintain

å A neural network can perform tasks that a linear program

å hen an element of the neural network fails, it can continue

å A neural network learns and does not need to be

å It can be implemented in any application.

å It can be implemented without any problem.

They may dominate us in the near future.

Sometimes it may cause the destruction of the "entire beautiful

The architecture of a neural network is different from the

Requires high processing time for large neural networks.

å Artificial Intelligence in the form of expert systems and

å Artificial intelligence has been used in a wide range of

å àeural àetworks are used in the recognition systems such

You might also like

| |

à |à |