| 摘要 |
Method and apparatus of error back-propagation for use in a neural network system. A first group (11) of processing devices (131, 132, 133) performs the resolving steps and a second group (12) of analogous processing devices (134, 135) performs the training steps while backpropagating errors calculated in a central processing device (10). The synaptic coefficient matrix Cij of the first group and the transposed matrix Tji of the second group are simultaneously updated. This updating of the synaptic coefficients can be performed by means of multipliers (341 to 34N) and adders (371 to 37N).
|
