The data input to neural networks is not always hard physical
measurements. It may include subjective responses, or membership
in ill-defined categories. Similarly, the response required may not be
a hard number. Some techniques for handling this sort of data are
discussed. Most importantly, this chapter shows how fuzzy processors
may be integrated with neural networks to improve performance
relative to what either could do alone.
280
Chapter 17
When a neural network is fed with physically measured exact data,
ther ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month, and much more.