An introduction to learning in web domains

摘要

Artificial neural networks have been the subject of massive investigation in the last twenty years. Theoretical studies on architectural and learning issues and experimental evidence are now clearly indicating their potential capabilities and their limitations. In a different, apparently unrelated field, the problem of ranking Web pages for information retrieval has been studied giving rise to solutions based on a dynamical systems, which very much reminds typical neural network dynamics. In this paper, we introduce the notion of learning in web domains, which represent an abstraction of the Web, giving insights on the way neural networks and Web page scoring systems can be bridged. Architectural and learning issues are discussed beginning from the theory of adaptive computation on structured domains.