Learn Weights from More than One Node

Update the input weights

We can refine a simple linear classifier by adjusting the slope parameter of the node’s linear function. We use the error, the difference between what the node produced as an answer and what we know the answer should be, to guide that refinement. That’s relatively easy because the relationship between the error and the necessary slope adjustment is very simple to calculate.

How do we update link weights when more than one node contributes to output and its error? The following figure illustrates this problem.