Team:Heidelberg/Modeling
From 2010.igem.org
(Difference between revisions)
(→Neural Network theory) |
(→Neural Network theory) |
||
Line 13: | Line 13: | ||
During the learning process the difference between the desired output (target) and the network output is minimized. This difference is usually called cost; the cost function is the measure of how far is the network output from the desired value. A common cost function is the mean-squared error and there are several algorithms that can be used to minimize this function. | During the learning process the difference between the desired output (target) and the network output is minimized. This difference is usually called cost; the cost function is the measure of how far is the network output from the desired value. A common cost function is the mean-squared error and there are several algorithms that can be used to minimize this function. | ||
- | [[Image:network.gif| | + | [[Image:network.gif|400px]] |
Figure 1: Normally Neural Networks are trained so that a particular input leads to a specific target output. | Figure 1: Normally Neural Networks are trained so that a particular input leads to a specific target output. |
Revision as of 00:18, 25 October 2010