Network Analysis in a Neural Learning Internet Agent

In recent years, with the massive increase in the amount of available online information on the Internet, a need has arisen for being able to organize and access that data in a meaningful and directed way. In this paper, special emphasis is placed on neural network approaches in implementing a learning agent for text routing. A brief summary of the various important approaches used is presented. An approach for neural learning internet agents is outlined, one that uses recurrent neural networks for the learning of classifying a textual stream of news information. In particular, we analyze the context of the internal memory and how it is relevant in making classification decisions.

@InProceedings{WAP00a,
 	 author =  {Wermter, Stefan and Arevian, Garen and Panchev, Christo},
 	 title = {Network Analysis in a Neural Learning Internet Agent},
 	 booktitle = {Proceedings of the International Conference on Computer Intelligence and Neuroscience},
 	 journal = {None},
 	 editors = {}
 	 number = {}
 	 volume = {}
 	 pages = {880--884},
 	 year = {2000},
 	 month = {}
 	 publisher = {None},
 	 doi = {}
 }