Hi Amal, if its a feed forward neural network that u intend to use, then u can only specify the values of inputs to the neurons in the input layer and output/response values to the neurons of the output layer. However one cannot specify values to the neurons of the hidden layer/s. The weighted inputs from input layer and the bias are summed up at each neuron of the hidden neuron. Then the computed output of the hidden nerons and the bias are weighted and summed up at each neuron of the output layer during the training stage. 

There are exact algorithms known for

document retrieval. A neural network

can hardly be better than an exact

algorithm.

Assume the case that the user enters

queries with one word each. Your

network would then answer with a list

of documents that contain the keyword.

But that can simply be achieved with

a hashtable or a tree. You're going

to spider your documents anyway.

Regards,

Joachim

I think u can use vector space model algorithm.

Go through this paper.

http://in.mathworks.com/help/images/ref/activecontour.html