9.5 BACKPROPAGATION
How does the neural network learn? As each observation from the training set is processed through the network, an output value is produced from the output node. This output value is then compared to the actual value of the target variable for this training set observation and the error (actual – output) is calculated. This prediction error is analogous to the prediction error in linear regression models. To measure how well the output predictions fit the actual target values, most neural network models use the sum of squared errors (SSE):
![equation](https://static.packt-cdn.com/products/9781119526810/graphics/images/c9-disp-0008.png)
where the squared prediction errors are summed over all the output nodes and over all the records in the training set. The problem is therefore to construct a set of model weights that will minimize the SSE. In this way, the weights are analogous to the parameters of a regression model. The “true” values for the weights that will minimize SSE are unknown...