-

The World Wide Web contains huge amount of dynamic, heterogeneous, and hyperlinked distributed documents. Many modern information retrieval systems are developed based on matching process, which is automated, but classification and query formulations are manual process. The approach taken in this paper is to add intelligence to Information Retrieval by way of Document Classification based on Vector Space Model using Inter-connected neurons with relevance feed back from the retrieved documents to the intelligent classifier as well as to the user query. The basic idea is to integrate three existing techniques: classification, query expansion and relevance feedback both to classified documents and user query to achieve a concept-based information search for the Web.