Practical Neural Network Recipies in C++

21

Optimizing the

Decision Threshold

When a neural network is used to make a decision, a threshold of

half-

activation is traditionally used. If it is possible to estimate reliably the

distribution of activation levels under both the null and alternative

hypotheses, we can often choose the threshold more intelligently.

390

Chapter 21

One of the most common uses for a neural network is to make a

yes-no decision. Does this blood sample test positive for leukemia? Is

that radar blip an aircraft? Does this person's financial history justify

issuin ...