Differences
This shows you the differences between two versions of the page.
| Both sides previous revisionPrevious revision | |||
| data_mining:neural_network:backpropagation [2017/08/19 20:27] – [Overfitting (How well does the network generalize?)] phreazer | data_mining:neural_network:backpropagation [2018/05/12 12:14] (current) – [Backpropagation] phreazer | ||
|---|---|---|---|
| Line 1: | Line 1: | ||
| ====== Backpropagation ====== | ====== Backpropagation ====== | ||
| - | We can compute how fast the error changes. | + | We can compute |
| Using error derivates w.r.t. hidden acitvities. Then convert error derivates to weights. | Using error derivates w.r.t. hidden acitvities. Then convert error derivates to weights. | ||