The goal of this paper is to explicitly address the question whether any true analogy exists between the central nervous system and the world wide web. By exploiting intuitive ideas of different fields ranging from neurobiology to sociology we investigate and present some properties of different evolving networks, whose dynamics is governed by the Hebbian learning rule. We intended to merge two different fields: the tools have been provided by the graph theory of evolving networks, while the properties of the Hebbian based learning rule is provided by computational neuroscience (CNS) models. We studied the emerging connection structure of purely feed-forward and feedback networks. The study will investigate approaches to alleviate performance limitations of large information management systems operating under the constraints of computational resources (computing power), communication bandwidth, and time. The main task will be to develop a global Function AP Proximator (FAPP) that will lead to optimised solutions for balancing the three constraints while assisting in the decision making process. The research will investigate methods for making 'rational choices' in a highly competitive environment, that can learn from experience, use previous examples to solve problems, and recognize novel examples where previous experience could be misleading. This methodology is comprised of three steps: (1) search fast, (2) efficiently remember what you have found, and (3) recognize if a new search is necessary (e.g., recognize novelty).