MAJUCLICK.com Online protal of Mohammad hammad Ali Jinnah University
MAJU,Mohammad Ali Jinnah University,MAJUClick,majuclick,maju toons,maju games,games,teachers,staff,about maju,about Mohammad Ali Jinnah University
MAJUCLICK.com Online protal of Mohammad hammad Ali Jinnah University
MAJU,Mohammad Ali Jinnah University,MAJUClick,majuclick,maju toons,maju games,games,teachers,staff,about maju,about Mohammad Ali Jinnah University
MAJUCLICK.com Online protal of Mohammad hammad Ali Jinnah University
MAJU,Mohammad Ali Jinnah University,MAJUClick,majuclick,maju toons,maju games,games,teachers,staff,about maju,about Mohammad Ali Jinnah University
MAJU Click [dot] COM
Live Testing... (Refresh the Page if you donot see the video for too long)
Contact: Admin@majuclick.com
WE
Need
Sponsors

WE
Need
Sponsors

WE
Need
Sponsors

WE
Need
Sponsors
Introduction to Neural Networks

Neural Processing
How do you recognize a face in a crowd? How does an economist predict the direction of interest rates? Faced with problems like these, the human brain uses a web of interconnected processing elements called neurons to process information. Each neuron is autonomous and independent; it does its work asynchronously, that is, without any synchronization to other events taking place. The two problems posed, namely recognizing a face and forecasting interest rates, have two important characteristics that distinguish them from other problems: First, the problems are complex, that is, you can’t devise a simple step-by-step algorithm or precise formula to give you an answer; and second, the data provided to resolve the problems is equally complex and may be noisy or incomplete. You could have forgotten your glasses when you’re trying to recognize that face. The economist may have at his or her disposal thousands of pieces of data that may or may not be relevant to his or her forecast on the economy and on interest rates.
The vast processing power inherent in biological neural structures has inspired the study of  the structure itself for hints on organizing human-made computing structures. Artificial neural networks, the way to organize synthetic neurons to solve the same kind of difficult, complex problems in a similar manner as we think the human brain may.

Neural Network
A neural network is a computational structure inspired by the study of biological neural processing. There are many different types of neural networks, from relatively simple to very complex, just as there are many theories on how biological neural processing works.

A layered feed-forward neural network has layers, or subgroups of processing elements. A layer of processing elements makes independent computations on data that it receives and passes the results to another layer. The next layer may in turn make its independent computations and pass on the results to yet another layer. Finally, a subgroup of one or more processing elements determines the output from thenetwork. Each processing element makes its computation based upon a weighted sum of its inputs. The first layer is the input layer and the last the output layer. The layers that are placed between the first and the last layers are the hidden layers. The processing elements are seen as units that are similar to the neurons in a human brain, and hence, they are referred to as cells, neuromimes, or artificial neurons. A threshold function is sometimes used to qualify the output of a neuron in the output layer. Even though our subject matter deals with artificial neurons, we will simply refer to them as neurons. Synapses between neurons are referred to as connections, which are represented by edges of a directed graph in which the nodes are the artificial neurons.

Output of a Neuron
Basically, the internal activation or raw output of a neuron in a neural network is a weighted sum of its inputs, but a threshold function is also used to determine the final value, or the output. When the output is 1, the neuron is said to fire, and when it is 0, the neuron is considered not to have fired. When a threshold function is used, different results of  activations, all in the same interval of values, can cause the same final output value. This situation helps in the sense that, if precise input causes an activation of 9 and noisy input causes an activation of 10, then the output works out the same as if noise is filtered out. To put the description of a neural network in a simple and familiar setting, let us describe an example about a daytime game show on television, The Price is Right.
Pomegranate NS08 Smart Phone

The Pomegranate NS08, before any of you get any ideas..
I want to clarify that no such device actually existent.

Nova Scotia created the rumor of the phone to get people to visit there site.The website is very realistic and actually very entertaining.I recommend you guys to visit it.
Site: www[dot]pomegranatephone[dot]com

It’s too bad that it doesn’t exist because a device like this would be all other phones out of business.

It is a very interesting concept, The site claims that Pomegranate NS08 does all the essential tasks an IPhone can do and more.
For instance, it can be a

    * Camera
    * Internet
    * GPS Navigation
    * Projector
    * Global Voice translator
    * Shaver
    * Coffee Brewer
    * Harmonica

WoW ! That is a great dream too bad it cant become reality..

Because No such device is possible..
Did Anyone have have ever seen the movie "Shorts" !?
Site: www[dot]imdb[dot]com/title/tt1100119/

We come across a same (so called vision) concept in it
But we must consider the practical side of it...
Which is impossible not in this shape and side that is..

and power, what about power !?...
our normal batteries won't last a single cup of coffee...
So we need some supper technology to store energy,

That looks good now what !?
Well now we need some kind of supper charger that charges the battery in at least 1hr from zero to full...
There is a glitch in it again...
Would we able to pay that much amount of electricity bill !? lolzz

and that is not the end of it...
so we need some new techs for the coffee maker
A small microwave emitting rod to make the coffee hot,
hmm, and what if our phone signals are disturbed because of the microwave !?
so we need a microwave shield,

Next...
Nothing first do that then I will ask more Questions...

So, We have to wait for these technologies to be available, and then wait longer so that they could be combined to make a "Pomegranate NS08"..
Logic Programming with PROLOG

    * Logic Programming

      Definition: A logic program is a finite set of rules
      The meaning of a logic program P, M(P), is the set of ground goals deducible from P.
    * Application Areas:

         1. Database
         2. Expert Systems
         3. Theorem Proving
         4. Natural Language Processing

A Prolog program is just a, Database consisting many clauses, a clause is either a fact or a rule

These facts & rules model a problem world by expressing relationship between things (NOT instructions).

    * PROLOG system are interactive and interpreted.
    * The interpreter is called an inference engine.
    * A programmer creates a database.
    * A user enters queries.

Examples:

A fact in the database
Father(anas,junaid).

father is a predicate. it represents a relationship between anas and junaid, which are called atoms(constant entities).

A query entered after the prompt ?-
?-father(anas,junaid).

The prolog system displays
YES

?-father(junaid,anum).

The prolog system displays
NO

Example Database

father(ali,anum).
father(junaid,farah).
father(junaid,ali).

mother(hira,farah).
mother(farah,rasheed).
mother(faiza,anum).

Variables may take any value.
Variables must start with UPPER CASE letter, e.g Parents.

Predicates(e.g father) and atoms (e.g junaid) are in lower case.


Example queries:

?-father(ali,X).
variable X is instantiated to the value,anum.

X=anum is displayed

Multiple Solutions

?- father(junaid,X).

gives
X=farah
on pressing ';' the next solution is produced:-
X=ali

Solutions are found starting at the top of the database.
Goals and Subgoals

The query

?- father(ali,anum).
is a goal that may succeed or fail.

A goal may consist of subgoals
for example, the query:
?-father(ali,anum),mother(hira,anum).

for this query,the goal, to success, both subgoals must successd.The extra ',' means AND logic.

?-father(X,farah),father(X,ali).
from the previous DB will display
X=junaid.

For each subgoal, search starts at the top of the database.

Backtracking

father(saad,ali).
Add above line at the top of the previous Database and consider the following query:
?-father(X,farah),mother(X,ali).

Search for the 1st subgoal: father(X,farah)
matches with: father(junaid,farah).
returns X=junaid
now the start of 2nd sub-goal father(X,ali).
it finds a match father(saad,ali).
it matches the result with X (junaid) and fails to find a match

now it backtrack to fine another match of previous subgoal
father(junaid,ali) is found on the end try
hence it will return,

X=junaid.
Rules in Prolog

Consider a database with some facts.

father(ali,anum).
father(junaid,farah).
father(junaid,ali).
mother(hira,farah).
mother(farah,rasheed).
mother(faiza,anum).

and the database also has some rule.

parent(X,Y):-father(X,Y).
parent(X,Y):-mother(X,Y).

which means, X is the parent of Y
if X is the father or mother of Y
alternatively:
parent(X,Y) is true, if father(X,Y) is true or if mother(X,Y) is true.

In a rule,
on the left is the conclusion, e.g parent(X,Y)
on the right is the condition, e.g father(X,Y)

Thus if the condition is true then the conclusion is true.

?-parent(hira,farah).
YES is displayed