Adaptive page ranking with neural networks

Recent developments in the area of neural networks provided new models which are capable of processing general types of graph structures. Neural networks are well-known for their generalization capabilities. This paper explores the idea of applying a novel neural network model to a web graph to compute an adaptive ranking of pages. Some early experimental results indicate that the new neural network models generalize exceptionally well when trained on a relatively small number of pages. Categories and Subject Descriptors: E.1 Data Structures: Graphs and networks. H.3.3.b Information Search and Retrieval: Information Filtering. I.2.6 Learning: Connectionism and Neural Nets. General Terms: Algorithm, Experimentation

• Type: Conference
• Year: 2005
• Where: WWW
• Authors: Franco Scarselli, Sweah Liang Yong, Markus Hagenbuchner, Ah Chung Tsoi
• Keywords: Internet Technology, Neural Nets, Neural Network Models, Neural Networks, WWW 2005