The Internet Search Engines Based on Artificial Neural Systems Implemented in Hardware would Enable a Powerful and Flexible Context-Based Research of Professional and Scientific Documents

摘要

This document describes a feasibility study on the development of a new generation of Internet Search Engines that should enable the professional user to search documents by complex contexts instead of single words linked by logical conditions. The method is well known in the literature and is, often, correlated to the WEB-SOM neural methodology. This paper approaches the problem with a new perspective that uses a hierarchical structure of the contexts and the latest neuromorphic VLSI chip technology. The user can search documents giving as input a reference document that is used by the neural search engine in order to find similar documents.The methodologies analysed in this paper share the same neuromorphic hardware technology and the responsiveness to the document context. However different architectural approaches are described. One of the proposed methods is based on a user-friendly X3D (successor of the Virtual Reality Modeling Language) GUI (Graphical User Interface). The other proposed methods use simpler GUIs that seem to be less attractive but, perhaps, more effective.