摘要 |
PROBLEM TO BE SOLVED: To efficiently handle multidimensional time-series data. SOLUTION: An input weight adjustment part 612 adjusts, for each dimension, an input weight factor inputted to an input layer unit of a dynamic approximation model, which is a dimension-based weight factor for input data that is time-series data observed of two or more dimensions. An output weight adjustment part 613 adjusts, for each dimension, an output weight factor outputted from an output layer unit of the dynamic approximation model, which is a dimension-based weight factor for output data of two or more dimensions. A determination part 711 determines, based on an output error for each node, a winner node that is a node retaining dynamics matched to input data. The recognition generation device is applicable to, for example, a robot. COPYRIGHT: (C)2008,JPO&INPIT
|