back·prop·a·ga·tion (b k pr p  -g shn)n. A common method of training a neural net in which the initial system output is compared to the desired output, and the system is adjusted until the difference between the two is minimized. |
Want to thank TFD for its existence? Tell a friend about us, add a link to this page, add the site to iGoogle, or visit the webmaster's page for free fun content.
| ?Page tools | ||
|---|---|---|
|