1
برق و الکترونیک::
پس انتشار
Multi-Layer Perceptron and Backpropagation 261
Multi-Layer Perceptron and Backpropagation
Rumelhart et al. published a groundbreaking article8 introducing the backpropagation training algorithm.9 Today we would describe it as Gradient Descent using reverse-mode autodiff (Gradient Descent was introduced in Chapter 4, and autodiff was discussed in Chapter 9).
reverse-mode autodiff algorithm in Appendix D, you will find that the forward and reverse passes of backpropagation simply perform reverse-mode autodiff.
The last step of the backpropagation algorithm is a Gradient Descent step on all the connec‐ tion weights in the network, using the error gradients measured earlier.
واژگان شبکه مترجمین ایران