| 摘要 |
A binary learning system consists of an input layer having binary input terminals, a coupling layer, a first binary gate layer with first similar logical elements, a second binary gate layer with second similar logical elements, and an output layer, so as to form a learning network. Each coupling condition between the adjacent layers is limited to a single direction from their inlet side to the outlet side, and each layer has independent routes without mutual coupling conditions. The coupling layer has means for selecting either one of a direct coupling condition and a coupling condition routed through an inverter, relative to routes from the respective signal units in the input layer to the respective signal units in the first binary gate layer. This selection is performed in such a manner that the selected coupling condition is adapted to eliminate or decrease the respective errors between original output signals at the output layer and monitor signals in the learning network.
|
