<XML><RECORDS><RECORD><REFERENCE_TYPE>15</REFERENCE_TYPE><REFNUM>8793</REFNUM><AUTHORS><AUTHOR>Cockshott,W.P.</AUTHOR><AUTHOR>Lambert,R.B.</AUTHOR><AUTHOR>Fryer,R.</AUTHOR></AUTHORS><YEAR>2003</YEAR><TITLE>Recognition system</TITLE><PLACE_PUBLISHED>US Patent 6505181</PLACE_PUBLISHED><PUBLISHER>N/A</PUBLISHER><LABEL>Cockshott:2003:8793</LABEL><KEYWORDS><KEYWORD>neural net</KEYWORD></KEYWORDS<ABSTRACT>A recognition system of the self-organizing artificial neural network type is arranged to classify input data according to stored categories which have been determined by a training process. In the training process the initial category representations are selectively iteratively updated in response to a series of training patterns and in accordance with a competitive learning routine. this routine uses measures of category utilization based on the proportion of all inputs received over a representative period, particularly long term utilisation and short term utilization, to ensure that all available categories will be used and that the system is stable.</ABSTRACT><URL>http://www.patentstorm.us/patents/6505181-fulltext.html</URL></RECORD></RECORDS></XML>