| 摘要 |
An adaptive processor for multi-source data fusion (30) comprises neural network adapted to receive at least three sets of inputs simultaneously. Three or more sets of inputs are directed to three or more sets of input neurons (44, 46, 48) respectively. The processor (30) is trained to produce an output (64) which is a rearrangement of the three inputs. By correlating the output with one of the other sets of inputs, a solution to an assignment problem is given. |
