专利内容由知识产权出版社提供
专利名称：Time-series trend estimating system and
method using column- structured recurrentneural network
发明人：Masahiro Matsuoka,Mostefa Golea申请号：US08/701700申请日：19960822公开号：US05956702A公开日：19990921
摘要：Each neural element of a column-structured recurrent neural network
generates an output from input data and recurrent data provided from a context layer ofa corresponding column. One or more candidates for an estimated value is obtained, andan occurrence probability is computed using an internal state by solving an estimationequation determined by the internal state output from the neural network. A candidatehaving the highest occurrence probability is an estimated value for unknown data. Thus,the internal state of the recurrent neural network is explicitly associated with theestimated value for data, and a data change can be efficiently estimated.
申请人：FUJITSU LIMITED
代理机构：Staas & Halsey, LLP
更多信息请下载全文后查看
